Patch

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

The description goes well beyond the annotations (destructiveHint=true) by detailing the atomicity: 'Nothing is written unless every hunk applies in file order with exactly matching context.' It also discloses a critical quirk: hunks are located by context, so line numbers may be off. This is essential behavioral information that the annotations do not provide.

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, front-loaded with purpose and behavioral nuance. Every clause earns its place; the critical atomicity rule and context-matching caveat are delivered without padding.

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 tool with three well-documented parameters, no output schema, and annotations covering destructiveness, the description supplies everything an agent needs: the exact operation, the single-file constraint, the atomicity guarantee, and the context-matching behavior. Nothing critical is missing.

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 complete descriptions for all three parameters (diff, path, dryRun) with 100% coverage. The tool description adds no additional parameter-level detail beyond what the schema states, so the baseline score of 3 applies.

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 opens with a precise verb and resource: 'Apply a single-file unified diff to one existing text file.' The analogy 'like git apply' anchors it firmly in a well-known operation, and the distinction of single-file vs. multi-file and the context-matching behavior clearly separate it from sibling tools like edit or replace_text.

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 makes it obvious when to use this tool: whenever you have a unified diff for a single file. It does not explicitly enumerate alternatives or exclusions, but the context is clear enough that an agent can infer the correct use case. The mention of 'existing text file' also implicitly signals it is not for new files.

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