polish_diff

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds context by stating no files are written, the tool re-verifies hypothetical polished lines, and leaves judgment-heavy findings in manual. This provides meaningful behavioral transparency beyond the annotations.

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 sentences, front-loaded with the primary action, and each sentence adds specific value. 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?

Given no output schema and 3 parameters, the description covers the tool's purpose, side effects, and return value (unified patch). It lacks explicit guidance on when to use versus alternatives, but is otherwise complete for the tool's complexity.

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 parameters well. The main description restates the diff parameter and mentions project/design_md, but adds little new semantics beyond 'without writing files' for context. 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 clearly states the tool reviews added UI-code lines and proposes deterministic DESIGN.md token substitutions without writing files. It distinguishes from siblings like review_diff by specifying the design token substitution focus and the requirement for the caller to apply the patch separately.

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 does not explicitly provide usage guidelines or mention when to use this tool versus alternatives like review_diff or evaluate_design. It states the output is a patch to be applied separately, but lacks contextual guidance on appropriate scenarios.

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