Patch

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

Beyond the destructiveHint annotation, the description discloses that the tool writes to a file, supports dryRun=true to preview without writing, and rejects multi-file diffs or diffs whose hunk context does not match. These are meaningful behavioral constraints that help the agent anticipate failures.

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?

Three tight sentences front-load the core purpose, then provide usage context, constraints, and the dryRun option. No filler or redundant explanation; every sentence 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 covers the required inputs, the key failure modes, and the safety dryRun option. Even without an output schema, an agent has enough information to invoke this tool correctly and to avoid common misuse.

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 the schema already documents path, diff, and dryRun. The description adds little beyond restating 'Pass { path, diff }' and the dryRun preview behavior, which is already in the schema. 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 states a specific action ('Apply a single-file unified diff'), the target resource ('to one file'), and the outcome ('write the result'). It also distinguishes itself from line-edit workflows by explicitly saying the diff blob should be passed directly, so an agent can differentiate this from sibling edit tools.

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?

It gives explicit when-to-use guidance: after inspecting a diff-tool dry-run. It also gives a clear when-not-to-use signal by saying 'instead of re-expressing it as line edits', and it describes rejection conditions for multi-file and mismatched diffs.

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