Judge Feedback

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

With no annotations, the description carries the full burden. It discloses that the tool returns a rubric that the agent must self-fill, and that it includes a compliance verdict. It does not mention whether the tool is read-only, stores data, or has side effects, but for a feedback tool this is likely non-destructive. The description adds value by explaining the interactive nature (self-fill) and the verdict, but it lacks detail on potential edge cases or error conditions.

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 concise sentence followed by a short instruction. It front-loads the workflow with 'How it works' and then a clear arrow representation. Every word contributes: input, output, scoring details, and timing. No redundancy or filler.

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 tool with one parameter and no output schema, the description covers the essential aspects: what to input, what to expect (rubric + verdict), and when to use it. It does not list the specific criteria in the rubric, but that is presumably returned by the tool itself. The description is sufficient for an agent to understand how to invoke it and interpret the result.

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 schema provides only the parameter name 'design_notes' with no description (0% coverage). The description compensates by explaining the input as 'paste design/code summary,' clarifying what design_notes should contain. This adds meaningful context beyond the schema. However, it does not specify format, length, or examples, so it is not exhaustive but adequate for a single string parameter.

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's function: it returns a scoring rubric and compliance verdict based on pasted design/code summary. The verb 'returns' and resource 'scoring rubric' are specific. It also mentions the self-fill nature and the 0-10 scoring, which distinguishes it from generic feedback tools. It does not explicitly name siblings, but the unique combination of rubric + verdict is clear enough to avoid confusion.

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 explicitly says 'Run BEFORE coding and BEFORE delivery,' providing clear timing guidance. It also implies the input is a design/code summary. It does not explicitly mention alternatives or when not to use it, but the timing is a strong usage signal. The flow 'How it works' also indicates the intended workflow.

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