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

Beyond the readOnlyHint annotation, it discloses input-handling requirements (preserve leading zeros, no prose in arguments), bounded sample behavior, and the full set of outputs including ranked candidates, deterministic warnings, clarification questions, and recommended geography_binding. It also notes cost ('Free... No payment required') and limitations.

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 and front-loaded, but contains a minor redundancy: 'Free geography utility' and 'No payment required' say the same thing. All other sentences earn their place, covering purpose, usage, output, and exclusions.

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 no output schema, the description thoroughly covers return behavior (ranked candidates, warnings, clarification questions, counts, recommended binding), scope limits, and cost. It is complete for a complex identification tool with 6 parameters and nested objects.

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 high (83%), so baseline is 3; the description adds actionable parameter guidance not in the schema: LLM clients must extract identifiers from natural-language and pass them as strings, preserve leading zeros, and not put prose in arguments. This complements the schema's existing field descriptions.

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?

Clearly states it 'Checks a bounded sample of identifiers against maintained reference indexes and geometry banks,' with a specific use case ('unsure which system, level, or bank they belong to') and explicit exclusions ('does not convert the full dataset or return polygons'), distinguishing it from conversion and geometry tools.

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?

Gives explicit when-to-use guidance ('Use it when a caller has geography keys but is unsure...') and when-not ('It does not convert the full dataset or return polygons'). It also provides concrete LLM client instructions for extracting identifier strings, which is valuable operational guidance.

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