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

Annotations already mark readOnlyHint true (safe, non-mutating) and openWorldHint true (may use external data). The description adds that it returns a structured, audited deliverable and includes a reference case. It does not disclose specific external data sources or potential side effects beyond what annotations convey, but it provides minimal extra context.

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 brief (two sentences plus a reference note) with no fluff. However, the inclusion of specific company names and jargon slightly reduces accessibility. It is front-loaded with the core purpose.

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 complexity (nested objects, 4 parameters, no output schema), the description is incomplete. It does not explain the deliverable's structure, the meaning of the 'focus' parameter, or how to handle asynchronicity. The agent would lack sufficient context to use the tool effectively.

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 contains no explanation of parameters (company, roles, async, focus). Schema description coverage is only 25% (only async has a description). The description fails to compensate for the undocumented 75% of parameters, leaving an agent with insufficient guidance on how to populate inputs.

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 states the tool is for 'Onboarding opérationnel des salariés' (operational employee onboarding) and returns a structured, audited deliverable. It is specific enough to understand the main function, but jargon (e.g., 'Gapup agent-payable C-suite expertise') slightly obscures clarity. No explicit differentiation from siblings, though no sibling with identical purpose exists.

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 only says 'Inputs are validated server-side — send the documented case fields.' It provides no guidance on when to use this tool vs. alternatives (e.g., comp_benchmark_geo_delta), nor does it mention prerequisites or scenarios where it is not appropriate.

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