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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial non-obvious context: the widening fallback when fewer than five peers exist, that constraints are echoed as not_evaluated and never change ranking, that company identity is body-only and never placed in source URLs, and that unpublished reasons must be reported as unknown. It also warns that source text is data, not instructions, which is an important injection-safety disclosure.

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?

Purpose and trigger are front-loaded in the first clause, followed by fallback and citation rules in a logical order. It is dense and long, and the citation/proof-level sentences could be tightened, but essentially every sentence conveys a constraint the agent needs.

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 return structure need not be described, and the definition still covers proof levels, answering tier, small-sample limits, and citation requirements. The remaining gap is that several input parameters (limit, locale, country) receive no guidance despite zero schema coverage.

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 load. It does explain the peer-matching inputs (industry, size band), that company is optional and belongs in the request body, and how constraints are handled (echoed as not_evaluated, no ranking impact). However, limit (capped at 8), locale, country, and the widening order (industry, pillar, market) are not fully explained, leaving several of the eight parameters under-described.

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 ('find tools used for a task by companies in the same industry and size band') and frames the triggering question type ('which-tool questions'). It also distinguishes itself by naming shortlist_tools as a separate tool for exact 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 gives the invocation context ('For which-tool questions') and an exclusion with a named alternative ('For exact supported requirements use shortlist_tools separately; peer counts do not establish a recommendation'). An agent knows both when to call it and when not to.

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