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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the return value ('return the patched result') but does not disclose what happens on invalid patches, whether the patch is applied exactly or with fuzzing, error handling, or any side effects. This lack of detail is a significant gap for a tool that operates on potentially malformed input.

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 a single sentence that is direct and front-loaded. It states the action ('Apply a unified diff patch') and the result ('return the patched result') with no unnecessary words. 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?

For a simple two-parameter tool, the description covers the core operation and output. However, it omits important context such as error behavior, patch format assumptions (beyond 'unified diff'), and whether the operation is destructive or reversible. Given no annotations and no output schema, this leaves the agent without critical edge-case knowledge.

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 input schema already provides descriptions for both parameters ('original' and 'patch'), covering 100% of the schema. The description adds no additional semantic meaning beyond what the schema states, so the baseline of 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: 'Apply a unified diff patch to an original text and return the patched result.' This clearly states what the tool does and differentiates it from sibling tools like diff_stats or patch_validate, which compute diffs or validate rather than apply patches.

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 implies the use case (applying a patch) but provides no explicit guidance on when to use this tool versus alternatives. There is no mention of exclusions, prerequisites, or when to prefer siblings like patch_validate or three_way_merge. The usage context is clear by inference, but not explicitly stated.

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