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

The description directly contradicts the annotations. Annotations set openWorldHint=true, implying external access, but the description says 'no external research or outbound actions'. Similarly, destructiveHint=true conflicts with the non-destructive nature of building a model and returning a draft. Per the rule, any contradiction yields score 1. The description does add valuable behavioral context (price, payment authorization, draft for review) but the contradiction overrides that.

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 concise and front-loads the primary action. It includes necessary operational details (price, payment requirement, draft output) without verbosity. Each sentence adds relevant information. It could be marginally more structured, but it is efficient and appropriate in length.

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 5 parameters, a nested required object, and no output schema, the description is too thin. It fails to explain the meaning and format of the parameters, how payment authorization works, or what the returned draft looks like. The agent would lack essential details to use the tool correctly, especially given the contradiction with annotations.

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 0%, so the description must compensate for the meaning of the parameters. It does not. The description mentions 'supplied volumes and processing times' but does not map them to the actual parameters (brief, source_text, audience, result_expires, idempotency_key, etc.). The nested 'input' object with 'brief' and 'source_text' is not explained, leaving the agent to guess how to populate fields correctly.

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 specific verb and resource: 'Build a capacity model from supplied volumes and processing times'. It clearly states the input and the expected deliverable, and the scope ('showing assumptions and missing inputs') distinguishes it from generic planning tools like account_plan or staffing_requirements. The title and name reinforce 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?

While the description notes that only buyer-supplied information is used and no outbound actions are taken, it does not explicitly state when to choose this tool over siblings such as account_plan or staffing_requirements. There is no mention of alternative tools or conditions that would make another tool more appropriate, so the agent gets no routing guidance.

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