compare_topic

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

Annotations cover readOnly/openWorld, and the description adds rich behavioral detail beyond them: the grouped-by-family return format, the not_loaded / in_documents_folder / not_in_documents_folder reporting, the semantics of coverage: "weak", and the caveat that coverage is judged only on keyword matches.

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?

Front-loaded with the purpose and example, then per-parameter guidance, then return-shape notes. Dense but nearly every clause adds operational value; the return-format paragraph is slightly long but earns its place given no output schema.

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 no output schema and 0% param coverage, the description covers everything: purpose, argument conventions, return structure, coverage semantics, and how to follow up with sibling tools. An agent could call and interpret this correctly without opening anything else.

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 coverage is 0%, so the description must carry the burden and it does: it defines topic (subject only, no standard names), doc_ids (which standards, omit for all), and the example values for each. Only limit is not explained, but the critical parameters are fully disambiguated.

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?

Specific verb+resource: 'side-by-side search of one topic in several standards', with a concrete example (ECSS vs NASA on factors of safety). Naming the ECSS/NASA pairing and the compare-across-standards scope distinguishes it clearly from search_requirements.

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?

Explicitly instructs how to build the topic argument ('the subject only... no standard names'), when to omit doc_ids ('omit for all loaded'), and what to do with weak coverage ('say so rather than force an equivalence'). It even routes post-search work to get_requirement / get_table, giving explicit alternatives.

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