commit_changes

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It fully explains the requirement for user approval, the execution of the commit, and the expected return (success message with commit hash or error). It also warns not to call the tool prematurely, ensuring safe usage.

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 appropriately sized and well-structured: it starts with the purpose, then provides a critical numbered workflow, followed by parameter details and return value. It is slightly verbose due to explicit step-by-step instructions, but every sentence is meaningful and earns its place.

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?

The description is comprehensive for the tool's complexity: it covers the workflow, parameters, and return value. Although an output schema is not provided in the data (context says 'Has output schema: true' but no schema shown), the description concisely states 'Returns: Success message with commit hash or error,' which is sufficient for a straightforward commit operation.

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?

The description adds significant meaning beyond the input schema: it specifies that the message should follow the 50/72 rule, clarifies that user_approved must be True and represents user consent, and explains that repo_path is optional and defaults to Claude's working directory. This compensates for the 0% schema description coverage.

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 clearly states 'Execute git commit with a user-approved commit message,' specifying the action (commit), resource (git), and the key condition (user-approved). It is distinct from sibling tools like get_commit_context (diff retrieval) and create_pr (pull request creation).

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 provides a detailed, step-by-step workflow that must be followed exactly, including calling get_commit_context first, generating and showing a commit message to the user, obtaining approval, and only then invoking this tool with user_approved=True. It explicitly states 'DO NOT call this tool in the same response where you generate the commit message,' providing clear guidance on when to use it.

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