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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds that inputs are validated server-side and that a structured, audited deliverable is returned, which provides some behavioral context. However, it does not discuss limitations, response time, or potential side effects, though the read-only nature is consistent.

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 short but includes promotional content (reference case with Spendesk and specific metrics) that does not help an AI agent select or invoke the tool. The core purpose is front-loaded, but the reference case is unnecessary fluff, preventing a higher score.

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 tool has nested object inputs, no output schema, and only a vague promise of a 'structured, audited deliverable.' It does not mention the async option, output format, or any invocation details beyond 'documented case fields.' For a complex tool, this is insufficiently complete.

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 17% (only async has a description), leaving 5 required and 1 optional parameter undocumented. The description says 'send the documented case fields' but does not elaborate on what those fields mean or how to fill them. It fails to compensate for the low schema coverage.

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 clearly identifies the tool as a paid advertising optimizer (Optimiseur de publicités payantes) and states it returns a structured, audited deliverable. It distinguishes itself with CMO-level expertise and a specific reference case, but does not explicitly compare against sibling tools like marketing_roi_dashboard or seo_cro_audit.

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?

There is no guidance on when to use this tool versus alternatives. The description mentions 'send the documented case fields' but does not explain scenarios, prerequisites, or exclusions. The reference case is illustrative, not prescriptive.

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