Apply Patch

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

Adds context beyond annotations: single-file throws, multi-file best-effort with results array, recommends regenerating patch on failure. No contradiction.

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 sentences, front-loaded purpose, each sentence adds essential behavioral info or workflow. No redundancy.

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?

Covers purpose, workflow, failure modes, and suggestions. Output schema present for return values. Complete for a patch tool.

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 coverage is 100%, description adds value for 'patch' by specifying generation with diff_files, but other params rely on schema. Baseline 3, plus credit for workflow context.

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?

Clearly states the tool applies a unified diff patch to files. Distinguishes single-file vs multi-file behavior and aligns with sibling tools like diff_files.

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?

Provides explicit workflow: diff_files → apply_patch(dryRun:true) → apply_patch. Explains failure modes per file type. No explicit when-not-to-use vs edit, but workflow is strong.

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