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

Annotations already mark it read-only, open-world, and idempotent; the description adds substantial beyond-annotation behavior: TF-IDF + cosine similarity, which fields are searched, no embedding API calls, 5-minute cache, public-scope restriction, score thresholds, and API-key behavior. 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?

Every sentence adds information: usage modes, constraint, algorithm, caching, scope, scoring thresholds, and auth context. The most important usage rule (exactly one of query/domain_id) 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?

Covers algorithm, data scope, auth, caching, and score interpretation. The only notable gap is return-value shape/ordering of results, which matters because no output schema is provided. Still highly actionable overall.

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 has 0% description coverage, so the description carries the burden. It explains query vs domain_id semantics, the exclusivity constraint, and api_key behavior. Limit is left to its self-evident name/defaultaiman, and the score-threshold guidance isn't tied explicitly to a parameter, but overall compensation is strong.

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?

Opens with a specific verb+object ('Find public domains most similar to...') and immediately clarifies the two input modes (query vs domain_id). The purpose is unambiguous and does not overlap confusingly with sibling 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?

Clearly instructs when to use query vs domain_id, states that exactly one is required, and notes the public-endpoint versus /mcp/mcp auth difference. It does not explicitly name sibling alternatives, but the selection logic is explicit and actionable.

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