创建真实提交

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false. The description adds meaningful behavioral context beyond these: it states the tool runs a secret safety scan, stages only exact selected paths, rejects stale HEAD/branch or unrelated staged files, and verifies the committed path set. Crucially, it explicitly states 'This tool never pushes' — a valuable safety disclosure. It stops short of describing failure modes, rollback implications, or side effects on working tree, but with annotations present the added value is solid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single tightly-packed sentence listing the exact steps and guarantees, ending with the explicit 'never pushes' disclaimer. Every phrase carries meaning — no filler, no redundancy. It is front-loaded with the most important behavioral guarantee (safety scan, exact path staging) and closes with a key safety boundary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a rich input schema (100% coverage), an output schema, and detailed annotations, the description covers the operational pipeline well. It explains validation flow (expected_head_sha, validation_refs from git_prepare_commit), staging constraints, and the no-push boundary in context of its siblings. Given the tool's complexity (a mutating commit op with safety checks), it is reasonably complete, though it could add what happens on verification failure or the exact revert path.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are well-documented in the schema. The description adds cross-parameter meaning by explaining that expected_head_sha, expected_branch, and validation_refs are values returned by git_prepare_commit (establishing the workflow contract), and that conversation_id/workspace_generation are auto-injected with mismatches rejected. This links parameters to the overall commit pipeline coherently.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific, multi-step verb+resource action: 'Run a secret safety scan, stage only the exact selected paths, reject stale HEAD/branch or unrelated staged files, create one real commit, and verify the committed path set.' This clearly distinguishes from siblings like git_prepare_commit, git_push, and git_finalize which occupy different stages of the commit pipeline. It makes the commit behavior explicit and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies this tool is the actual commit-creation step (as opposed to git_prepare_commit for preparation and git_push for pushing). It states 'This tool never pushes,' which is a useful exclusion clarifying it won't perform the push stage. However, it doesn't explicitly name alternatives or give when-to-use/when-not-to-use guidance beyond these implicit stage divisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.