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

Annotations already declare read-only, idempotent, non-destructive and closed-world, and the description is consistent with that fixed dataset. It adds useful behavioral context beyond the annotations: what each result contains (figure, unit, scope, source chain, Wayback archive, verification dates, permanent URL) and the quoting/confidence preference. No rate limits or pagination behavior is mentioned, keeping it at 4.

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 core purpose and dataset scope, then result shape, then the get_stat hand-off and examples. It is a bit dense in the middle field list, but each clause carries information an agent needs; no filler.

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?

An output schema exists, so the heavy enumeration of result fields is somewhat redundant, but the description still supplies the confidence/source-type semantics and quoting guidance an agent needs to use results correctly. The only gap is that limit and the unfiltered-search behavior aren't clarified.

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 40%; query and topic are documented in-schema, while confidence, source_type and limit lack descriptions. The description partially compensates by explaining confidence semantics ('prefer high-confidence primary sources') and implying topic filtering via the 'topic="labour"' example, but it never clarifies the limit parameter or the confidence/source_type enum meanings beyond what the enum itself shows.

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 (search) and resource (citable robot statistics), enumerates the domains covered and the fields each result carries, and names the sibling get_stat for the deeper-detail path. An agent can distinguish it from get_stat or search_use_cases without opening any schema.

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?

Gives concrete query examples and explicitly routes to get_stat when the verbatim quote or citation is needed, plus guidance to prefer high-confidence primary sources. It stops short of stating when NOT to use the tool (e.g., vs search_use_cases or the provider tools), so not a full 5.

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