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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds context: it calculates a Wilson confidence interval, works with aggregate counts, and is not legal advice. No contradictions.

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?

Four sentences with clear front-loading: purpose, usage condition, alternatives, disclaimer. No unnecessary words. Could be slightly more structured but efficient.

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 statistical nature and presence of an output schema, the description adequately covers purpose, inputs, and usage boundaries. Missing details like output structure are covered by the schema. Assumptions and formula are not essential for tool selection.

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 0%; description compensates by explaining parameters are counts from a fixed reference set and mentions confidence_level implicitly via Wilson interval. However, it does not explicitly describe each parameter's format or default values beyond schema properties.

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?

Description specifies exact function: 'Calculate recall against a known control set' with details about computing the share of confirmed relevant documents found and Wilson confidence interval. It explicitly distinguishes from sibling tools like calculate_review_metrics and calculate_tar_recall_estimate.

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?

Explicit when to use: 'Use when you have relevant-found and relevant-missed counts from a fixed reference set.' Provides exclusions with named alternatives for confusion matrix and discard-set sample contexts. Includes disclaimer 'not legal advice.'

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