ChatCompletionsRequest drops MCP tool parameter schemas from parametersJsonSchema
メンテナーはふだん 1 日以内に返信
評価
この issue はまだ評価されていません。
説明
🔴 Required Information
Describe the Bug:
ADK's native McpToolset is unusable with the native chat-completions connector for MCP tools that take parameters.
AbstractMcpTool declares MCP tool input schemas through FunctionDeclaration.parametersJsonSchema(...), but com.google.adk.models.chat.ChatCompletionsRequest reads only FunctionDeclaration.parameters().
When only the raw JSON schema is populated, the chat-completions path falls back to an empty parameter schema:
{
"type": "object",
"properties": {}
}
As a result, the model receives a parameterless tool declaration for an MCP tool that actually requires arguments and commonly calls the tool with {}.
This appears to be an incompatibility between two first-party core/ ADK components rather than a consumer configuration issue.
Steps to Reproduce:
-
Create an MCP tool with a required parameter, for example:
{ "type": "object", "properties": { "jobId": { "type": "string" } }, "required": ["jobId"] } -
Expose the MCP tool through ADK's native
McpToolset/AbstractMcpTool. -
Use the tool with a model backed by
ChatCompletionsHttpClient. -
Inspect the outbound
/chat/completionsrequest. -
Observe that the generated tool declaration contains an empty parameter schema instead of the MCP tool's JSON schema.
Expected Behavior:
The outbound OpenAI-compatible tool declaration should preserve the MCP tool's parameter schema, including its properties and required fields:
{
"type": "function",
"function": {
"name": "analyze_premerge_failures_by_job",
"parameters": {
"type": "object",
"properties": {
"jobId": {
"type": "string"
}
},
"required": ["jobId"]
}
}
}
The model should therefore be able to identify jobId as a required argument and provide it when calling the tool.
Observed Behavior:
The outbound declaration contains an empty schema:
{
"type": "function",
"function": {
"name": "analyze_premerge_failures_by_job",
"parameters": {
"type": "object",
"properties": {}
}
}
}
The model cannot see that jobId exists and commonly emits an empty argument object:
{}
This prevents parameterized MCP tools from being used correctly through the chat-completions connector.
🟡 Optional Information
Regression:
No known regression has been established. The issue is observed with ADK 1.7.1.
Logs:
The relevant evidence is the outbound /chat/completions request. The tool declaration contains the following schema instead of the MCP-provided schema:
{
"type": "object",
"properties": {}
}
Screenshots / Video:
N/A.
Additional Context:
FunctionDeclaration supports two representations for function parameters:
- typed
parameters(Schema) - raw
parametersJsonSchema(...)
AbstractMcpTool populates the raw parametersJsonSchema form for MCP tool input schemas. ChatCompletionsRequest currently consumes only the typed parameters(Schema) form.
We also observed the same raw-only declaration shape through an application-side MCP adapter, but the native McpToolset reproduction demonstrates that the issue does not depend on that adapter.
A closely related fix already exists for the Claude connector in PR #1342 / commit 760c8da. That fix forwards the raw schema directly, preserving JSON Schema constructs such as $ref and $defs.
OpenAI-compatible chat-completions APIs also accept raw JSON Schema, so forwarding parametersJsonSchema directly appears preferable to converting it into the narrower typed Schema representation.
Impact:
Any parameterized MCP tool is affected when used through the chat-completions connector. In our case, this blocks:
- a tool accepting
jobId - parameterized architecture-analysis MCP tools
Zero-argument tools continue to work because their empty schema is valid.
Temporary Workaround:
Until ADK is fixed, we materialize the raw schemas into typed parameters(Schema) in our BaseLlm implementation before delegating to ChatCompletionsHttpClient.
This workaround is connector-local and is covered by a wire-level regression test.
Minimal Reproduction Code:
A minimal reproduction should consist of:
// Create an MCP tool whose input schema contains a required parameter,
// expose it through the native McpToolset, and invoke it through
// ChatCompletionsHttpClient.
//
// The outbound /chat/completions request contains:
// {
// "type": "object",
// "properties": {}
// }
// instead of the MCP tool's declared schema.
The important distinction is that the MCP tool declaration populates parametersJsonSchema(...), while ChatCompletionsRequest currently reads parameters().
How often has this issue occurred?:
- Always (100%)
- 主要言語
- Java
- スター
- 1.7k
- フォーク
- 431
- 平均マージ
- 2日 15時間
- マージ済み PR(30日)
- 33
環境構築
このプロジェクトの開発コンテナを、あなたの GitHub アカウントでブラウザ上に起動します。
- Dockerfile・Docker Compose ファイルなし
- プルリクエストのテンプレートあり
- コントリビューションガイドを読む
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
google/adk-java のほかの issue
-
難易度 2/5 1〜3時間 初心者へのやさしさ 76/100
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 84/100
メンテナーはふだん 1 日以内に返信
-
難易度 5/5 1週間以上 初心者へのやさしさ 35/100
メンテナーはふだん 1 日以内に返信
-
BaseLlmFlow nests each step inside the previous one and overflows the stack after a few hundred LLM calls対応中かも @hemasekhar-p が 6 日前に担当しました。 オープンneeds review
難易度 4/5 3〜5日 初心者へのやさしさ 68/100
google/adk-java#1564 · コメント 1 件 · 担当者 1 名 ·
メンテナーはふだん 1 日以内に返信
-
Approved tool call re-runs on every later user turn if it never got a function response対応中かも @hemasekhar-p が 9 日前に担当しました。 オープンneeds review
google/adk-java#1556 · コメント 1 件 · 担当者 1 名 ·
メンテナーはふだん 1 日以内に返信
google/adk-java の issue をすべて見る
似ている issue
-
bug status: needs triage
難易度 2/5 1〜3時間 初心者へのやさしさ 66/100
LawnchairLauncher/lawnchair#7360 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信
-
Temporal transforms put pre-epoch timestamps at `.999999` into the previous unit対応中かも このイシューにリンクされたプルリクエストがオープン中、またはマージ済みです。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 76/100
apache/iceberg#18371 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 80/100
objectionary/hone-maven-plugin#1297 ·
メンテナーはふだん 1 日以内に返信
-
bug documentation iam
難易度 1/5 1時間未満 初心者へのやさしさ 90/100
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 82/100
objectionary/lints#1541 ·
メンテナーはふだん 1 日以内に返信