Recommend classifications

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false. The description adds genuine value by asserting determinism and that results are a shortlist for user choice rather than an automatic pick, but says nothing about ordering criteria, result size behavior, or failure modes.

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?

Three short sentences with no filler, and the core behavior (ranked shortlist, advisory not automatic) is front-loaded. Slightly clipped phrasing ('Include answer options and context') costs it the top mark.

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?

An output schema exists, so return-value explanation is not required. Still, with four parameters at 0% schema coverage, the description documents only two of them obliquely and never explains the required question_text, leaving the agent to infer how to frame a call.

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 0%, so the description must compensate. It does partially: 'Include answer options and context' maps to the answer_options and survey_context parameters, giving an agent a hint about their role. However, the required question_text and the limit/cap behavior are not addressed.

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?

States a specific verb ('Return a deterministic ranked shortlist') and resource ('classification concepts and codelists'), which distinguishes it from list_classifications and search_codes by the notion of relevance ranking. It never names a sibling explicitly, so the differentiation is inferred rather than stated.

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?

'Ranking supports user choice; it is not an automatic selection' clarifies that output is advisory, which is useful guidance. But it gives no explicit when-to-use condition versus alternatives like search_codes or browse_hierarchy, leaving the routing decision to inference.

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