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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses that data is 'read from the open web-features dataset at build time,' implying a potential staleness caveat. It also transparently describes the exact return contents: baseline status, date, lacking browsers, site counts, @supports details, and fallback notes. This is rich behavioral context that complements the annotations without contradiction.

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 long but well-structured: it front-loads the two questions, then details the second question, then provides usage guidance with examples, and ends with the no-argument behavior. Each sentence serves a purpose—explaining scope, outputs, and use case. It is not overly terse, but the level of detail is warranted given the tool's complexity.

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?

There is no output schema, so the description must convey what the tool returns. It does so comprehensively: baseline status, date, lacking browsers, number of sites, which ones, @supports usage, exact conditions, and fallback notes. It also covers the Ship Gap scenario. While it doesn't specify a JSON structure or pagination, the output is well-scoped and sufficient for an agent to understand the result.

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 input schema already describes the parameter with examples and explicitly notes the omission behavior ('Omit for the whole Ship Gap summary'). The description adds usage context (before writing CSS) but does not materially expand on the parameter's format or semantics beyond what the schema provides. With 100% schema coverage, the description's additional value is marginal.

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 clearly states it answers two specific questions about a CSS feature: Baseline status and adoption across curated sites, with concrete examples of features it covers. It distinguishes itself from siblings by focusing on CSS feature support data rather than site decoding or theme retrieval. The verb 'answers' plus resource 'modern CSS feature' makes the purpose unambiguous and specific.

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 tells the agent when to call it: 'Call it before writing CSS that uses container queries, :has(), ...' This provides a clear usage trigger. It also explains the alternative behavior when no feature is given (returns Ship Gap). However, it does not explicitly mention when not to use it, though no sibling tool competes directly, so the guidance is adequate.

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