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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds substantial behavioral context: 'Coordinates are INPUT only — nothing is stored or logged,' 'deterministic distance sort,' the confidence scoring rule ('large airport within 25 km scores high; closed/heliport/seaplane results cap lower'), and the 429 retry behavior. These are non-obvious traits not derivable from annotations or schema.

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 organized into clear, purposeful sections: summary, input instructions, behavior, return envelope, limitations, and related tools. Each sentence contributes unique information (e.g., data source, rate limiting, navigation disclaimer). While longer than average, no redundant or filler content exists, and the most critical info (what it does and how to use) is front-loaded.

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's complexity (rate limits, confidence scoring, output envelope) and the presence of an output schema, the description is remarkably complete. It explains the return structure ('count and results[] ... under result, plus confidence, _source and citation'), the confidence semantics, rate-limit handling with retry headers, and the reference-data limitation. This exceeds what schema and annotations alone provide.

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 100%, so the baseline is 3. The description adds only marginal parameter context beyond the schema: it reiterates latitude/longitude format, lists optional parameters (radius_km, max_results, type), and gives an example value for type ('e.g. large_airport only'). It does not provide new semantics like edge-case warnings or format specifics not already in the schema.

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 action: 'Find the airports nearest to a caller-provided latitude/longitude, sorted by great-circle (haversine) distance with distance_km on each result.' This clearly identifies the resource (airports) and the unique value (proximity sorted by distance). It also distinguishes itself from sibling tools via the 'Related' section, naming airport_lookup as exact code/name lookup with no distance, and unlocode_lookup as named transport-location search.

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 explicitly states when to use the tool ('pass coordinates you already hold'), when not to use it ('does NOT geocode place names and does NOT compute routes'), and names alternatives ('Related: airport_lookup... unlocode_lookup...'). It also provides practical guidance on rate limits: 'back off and retry, or call get_subscribe_link for higher limits.' This goes beyond implied usage.

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