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

No annotations are provided, so the description must carry the full burden of disclosing behavior. It mentions 'page' and filtering but does not describe the exact output format (e.g., list of entries, pagination metadata, error behavior). It also does not explicitly state that it is read-only, though the name and context imply it. This lack of detail limits transparency.

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 two sentences with three concrete examples and a clear instruction about combining with q. No redundant words; it is efficient and to the point.

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?

No output schema is provided, so the description should explain what the tool returns. It only says 'page of one catalogue' which is vague. It does not describe the structure of entries or whether pagination information is included. Given the lack of an output schema, this is a significant gap.

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?

Kind, lang, and filters are described in the schema, and q is clarified as a name search in the description text. However, limit and offset have no description, and filters' allowed fields are only listed indirectly via the schema's description. The overall coverage is moderate, leaving users to guess the effect of offset and the exact matching rules for filters.

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 that the tool lists a page of a catalogue with filters and gives concrete example queries (e.g., 'cubic and gem-quality' minerals) that illustrate the intended use. It does not explicitly name sibling tools, but the examples make the purpose distinguishable from list_facets (which lists filter values) and get_entry (which fetches a single entry).

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?

It provides three example user intents and instructs to combine with q for a name search inside the filter, offering practical guidance on when to apply the tool. However, it does not contrast with alternatives like search_encyclopedia or get_entry, so the guidance is implicit rather than explicit.

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