discover_competitors

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

The description aligns with the readOnlyHint and openWorldHint annotations—it searches external sources and returns results without side effects. It additionally explains the internal methodology (text-pattern heuristics, mention frequency, listed-company signal) and the deterministic top-5 selection, going beyond the annotations to provide insight into how the tool behaves.

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 a single sentence, but it packs in multiple steps (search, extract, rank, return) and a caveat about deterministic selection. While it is somewhat long, it remains focused and avoids unnecessary fluff, earning a high score for conciseness with minor structural complexity.

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?

The description clarifies that the tool returns a top-5 list and explains the ranking logic, covering the output aspect despite no output schema. However, it does not address how to specify the search target (company vs sector) or other contextual fields, leaving some ambiguity in how to pass the 'context' parameter. Overall, it is reasonably complete for the tool's core purpose but misses parameter-level context.

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?

The description does not reference any of the parameters in the 'context' nested object, nor does it explain how to populate them (e.g., when to provide 'company' vs 'sector'). The schema itself has descriptions for only two fields (sector, companyDomain), leaving others undefined, and the tool description adds no clarification. This leaves the agent guessing about required inputs for a nested structure.

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 explicitly states the tool's function: searching industry-analyst and news sources for competitors, extracting candidates, ranking them, and returning a top-5. The verb 'searches' and specific details about the process make the purpose unmistakable, and the deterministic selection note distinguishes it from other tools that might involve model choice.

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?

The description implies the tool is for discovering competitors but does not explicitly state when to use it over alternatives. It mentions 'instead of leaving selection to the calling model,' which hints at deterministic behavior, but there is no direct guidance on when to invoke this tool versus others like search_company or comparables_valuation. The context is clear enough for an agent to infer, but explicit guidance is lacking.

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