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

Annotations include readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description goes well beyond this by disclosing the fuzzy match quality reporting mechanism (confidence, FUZZY_BEST_MATCH, NO_MATCH advisories), rate-limiting with 429 retry behavior, and the provenance verification caveat. It also clarifies that no results return a count of 0 rather than an error. No contradiction with 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 longer than many, but it is purposefully structured: lead with core search capability, then parameter semantics, then behavioral details, then returns, then limitations, then related tools. Each sentence carries information—rate limits, advisories, provenance status, and alternatives. It is front-loaded with the primary use case and is dense without bloat, though a slightly more compact format would be possible.

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 optional parameters, an output schema, rate limiting, and data provenance caveats, the description covers everything an agent needs: input selector rules, match-quality advisories, rate-limit handling, response fields, verification limitations, and sibling tool comparisons. The presence of an output schema removes the need to enumerate full return types, but the description still summarizes the result structure and envelope details usefully.

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?

The schema already covers parameter formats and descriptions 100%, providing a baseline of 3. The description adds crucial usage semantics: it states the mutual exclusivity of parameters ('Provide ONE parameter'), explains that `query` is a ranked fuzzy search while others are exact filters, and provides a concrete AWB prefix example ('176 = Emirates'). This meaningfully enhances the schema's bare field names and patterns.

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: 'Search 6,357 airlines by name, IATA code, ICAO code, AWB prefix, or country.' It immediately clarifies scope and domains, and explicitly distinguishes itself from sibling tools by noting 'airport_lookup (searches AIRPORTS, not carriers)' and 'validate (checks an AWB number's check digit and names its airline from this dataset).' This is a textbook example of purpose differentiation.

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?

Provides explicit guidance: 'Provide ONE parameter' and distinguishes the ranked fuzzy search from exact filters. It names alternatives with their contrasting purposes ('airport_lookup' for airports, 'validate' for AWB check digit validation). It also explains expected outcomes for no-hit cases, giving clear when-to-use/when-not-to-use context.

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