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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is in result semantics: it discloses that only robots publishing every filtered figure match, that per-figure in-scope counts are returned, and that values compare in canonical units unless `unit` is supplied. That is genuinely useful non-obvious behavior; it stops short of covering paging or filter-count limits.

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 sentences, front-loaded with the core action and examples, and each sentence carries information (filtering, matching semantics, unit handling). The clause 'so a short list is never mistaken for everything that can do the job' is slightly discursive but earns its place as a caveat.

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?

For a 7-parameter, no-output-schema tool, the description covers the essential filtering model, matching rule, unit conversion, and return-shape caveat. Gaps are minor: no mention of pagination defaults or the maxItems=8 filter limit.

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?

With schema description coverage at only 43%, the description carries real weight: it explains the filter min/max/equals model, the `unit` conversion parameter, attribute keys (tying them to list_attributes), and sorting. It leaves `limit`, `offset`, `order`, and the 8-filter cap to the schema, which are mostly self-explanatory defaults.

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 and resource: filter robots by published figures, with concrete examples (payload ≥ 20 kg, reach ≥ 1300 mm). It is clear this is a numeric/figure-based lookup, but it never names search_robots or get_robot, so the agent must infer the boundary from the sibling list alone.

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?

Usage context is implied by 'optionally within a category or maker' and the figure-filtering examples, which suggests when this tool fits. However, there is no explicit when-not guidance and no mention of the obvious alternative (search_robots) for keyword-style lookups, so routing remains inferential.

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