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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly states what the tool returns (name, domain, kind, verdict, etc.) and that it filters by several criteria, which implies it is a read-only query. However, it does not mention pagination, default limit (though the schema does), sorting, or any potential side effects (though none are expected for a search). The description is transparent about outputs but not about limits or error behavior.

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 a single, information-dense sentence that front-loads the purpose and then lists filters and return fields. It contains no filler and each clause adds value. It is concise enough for an agent to parse quickly, though it could be slightly improved with a bulleted list, but as prose it is effective.

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 has 7 parameters, no annotations, and no output schema, the description covers the essential aspects: what it returns and how it filters. It lists the return fields completely, which is crucial since there is no output schema. It does not mention default behaviors like the 25-item limit (which is in the schema) or any auth requirements, but for a search operation those are typically not needed. The description is sufficient for an agent to call the tool effectively.

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 86%, and the schema already documents each parameter (enums for kind, link, price, accepts; limit with default and range; query with maxLength). The description adds no additional parameter-level meaning beyond restating the filter categories. Since the schema does the heavy lifting, a baseline 3 is appropriate; the description does not clarify or expand on any parameter semantics.

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 states a specific verb ('Find') and a concrete resource ('directories, review sites, list sites, AI directories, launch sites, press and networks'), then lists explicit filters and return fields. It is clear and distinct from siblings like get_place, which suggests a single-place retrieval, whereas this is a broad search. The purpose is unambiguous and not a tautology of the tool name.

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 implies the tool is for searching directories and similar sites, and the filter list indicates when to use it. However, it does not explicitly state when to use this tool versus alternatives like get_place or where_is_app_listed, nor does it mention any exclusions or prerequisites. The context signals show this is the primary search tool, but the description leaves routing logic to the agent.

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