Run Sonnet-as-Judge

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

Annotations already indicate idempotency and non-destructiveness. The description adds that the tool returns a batch ID and stores results in a specific location, but it does not disclose side effects (e.g., whether existing results are overwritten), authorization requirements, or dependencies on prior classifications.

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 extremely concise—two sentences that first state the purpose and then the output. Every word is intentional, and there is no extraneous information.

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?

While the description covers the core function and output, it lacks completeness for a successful invocation. Missing details include what 'classified reports' are, whether results are immediately available or require polling, and any rate limits or prerequisites. Given the tool's simplicity, these gaps reduce completeness to merely adequate.

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 has 100% parameter descriptions (limit and projectId). The tool description does not add extra context for these parameters beyond what the schema provides, so it meets the baseline of 3 without adding value.

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 action: 'Run the Sonnet-as-Judge over a batch of classified reports.' It distinguishes itself from siblings by specifying a unique function (judging reports) and notes that it returns a batch ID and stores results in 'judge_results.'

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?

No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites, such as requiring reports to be classified beforehand, nor does it indicate situations where this tool should be avoided or what other tools might be more appropriate.

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