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

Annotations already indicate readOnlyHint=true and openWorldHint=true, so no contradiction. The description adds that inputs are validated server-side and that the deliverable is 'structured, audited', but it does not elaborate on the actual behavior beyond that, such as whether results are cached, how long they take, or what 'audited' means in practice. With annotations providing the safety profile, a mid-range score is appropriate.

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 compact and includes relevant information, but it is a single run-on sentence mixing French and English, which makes it harder to parse. It front-loads the purpose but meanders into a reference case and validation note without clear structural breaks. Not excessively long, but not well-organized.

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 the tool's complexity (nested objects, multiple params, async option, no output schema), the description is incomplete. It does not explain the expected input structure beyond a vague 'documented case fields', nor does it describe the deliverable's format, content, or how to handle the async flow. The reference case helps but leaves significant gaps for an agent needing to invoke the tool correctly.

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 description coverage is only 25% (only 'async' is described), so the description must compensate for the undocumented parameters (selfCompany, competitors, focus). It does not explain what these fields mean, how to structure them, or what values are acceptable beyond the schema's basic types. The phrase 'send the documented case fields' is vague and does not clarify the semantics of the parameters.

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 specifies a clear verb+resource: it produces competitor profiles in SWOT-style format and answers specific questions about competitor strengths, weaknesses, and positioning. It includes a concrete reference case (Notion vs. ClickUp, Asana, Coda), which helps clarify intent. However, it does not explicitly distinguish itself from nearby sibling tools like competitive_deep_dive or competitor_intel, so it misses the top score.

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 usage by providing example questions and a reference case, but it gives no explicit guidance on when to use this tool versus alternatives, nor any exclusions. It does not mention prerequisites, preferred scenarios, or tools not to use. This is essentially implied usage without clear decision rules.

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