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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds significant behavioral detail: 'this tool never raises a protocol error — it returns {"error": "..."}' and 'Every call is read-only and idempotent.' This enriches the agent's understanding of error handling and retry behavior 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 well-structured with clear sections: purpose, output summary, example, sibling distinction, and error handling. It is slightly verbose (e.g., the example output is lengthy), but every sentence contributes value. No redundancy or fluff.

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 the tool only has 2 parameters, the description fully covers purpose, input, output (including sample and error case), and compares to siblings. The presence of an output schema (implied by the sample) means the description does not need to explain return values in detail, but it does so anyway. The description is complete for an agent to select and invoke the tool correctly.

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 coverage is 100% with both parameters described. The description adds meaning by providing a concrete example of typical input and output, clarifying the expected format and what the tool returns. It also explains the default value for max_score and the requirement for minItems:1 in scores.

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 purpose: 'Summarize how an assessment landed: stats, bands, and outliers.' It specifies the verb (summarize/generate stats), the resource (assessment scores), and differentiates from the sibling tool readability_report by explicitly stating 'Not for the readability of the assessment itself.' The provided input/output example further solidifies the purpose.

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 gives explicit usage guidance: 'Use on a list of scores already earned. Not for the readability of the assessment itself (readability_report).' It also advises on error handling and retry safety: 'after correcting the input it is always safe to retry.' This clearly tells when to use this tool versus the alternative.

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