准备真实提交

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false. The description reinforces the read-only nature ('never stages, commits, or pushes') and adds that it 'binds to the current HEAD and validation evidence' and 'reports blockers' — useful context beyond annotations. It doesn't describe return format details, but those are covered by the output schema.

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?

Two sentences, zero waste. The first sentence states the action; the second sentence states the constraints. Every word 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?

Output schema exists and covers return values. The tool has 6 params but only 1 required, all well-documented in the schema. Annotations cover the safety profile. The description adds the HEAD-binding and blocker-reporting context that makes invocation decisions clear. Slightly more could be said about what 'blockers' means, but the overall picture is complete.

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%, with rich per-parameter descriptions (e.g., workspace_id being auto-injected and rejecting unknown/mismatched values, commit_message having no side effects, selected_paths defaulting to all changed paths). The description adds little beyond the schema because the schema already carries the full load. Baseline 3 is appropriate.

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 uses a specific verb+resource structure: 'Read the exact current change set, bind it to the current HEAD and validation evidence, and report blockers.' It clearly distinguishes from siblings like git_commit, git_push, and git_finalize by explicitly stating 'This tool never stages, commits, or pushes.'

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 states what the tool does and what it never does (stage, commit, push), giving clear context that it's a preparation/dry-run tool. The explicit 'never' statements help the agent know when NOT to invoke this, though it doesn't name alternative tools to use instead (e.g., pointing to git_commit for actual commits).

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