code.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显得. The [approval required][workspace write][risk:dangerous] tags convey safety-critical traits, and the branch restriction adds important context. However, it does not disclose whether the commit is local-only or pushed, how all changes are staged when paths is omitted, or what the return value looks like.

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 two compact sentences with no redundant wording. Safety markers are front-loaded, followed by the core action, a precondition, and the optional parameter, making it easy to scan and process.

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 covers the essential purpose, the branch precondition, and the risk profile, which is adequate for a simple commit operation. However, it leaves important behavioral details implicit, such as what happens when paths is not provided, whether the commit pushes to a remote, and how 'allowed' branches are determined. These gaps matter for a workspace-write tool with no output schema.

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 0%, so the description must compensate. It does explain the paths parameter as 'non-secret paths' to stage, adding meaning beyond the raw array type. However, it does not clarify path format or the default when paths is omitted, and the required message parameter receives no semantic explanation beyond its obvious purpose.

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 the action 'Commit changes' and distinguishes it from sibling tools like code.apply_patch, code.create_branch, and code.open_pr. The branch constraint and optional staging clarify exactly what the tool does and its scope.

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 phrase 'only while on an allowed feature/ai branch' provides an explicit precondition and implies that the tool should not be used on main or other disallowed branches. It does not explicitly name alternative tools, but for a commit operation the usage context is sufficiently clear.

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