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

Annotations already provide readOnlyHint=true, but the description adds value by stating it is 'Gratuit' (free) and explains the output structure (grouped by level, sorted by gain, with IDs). This provides behavioral context beyond annotations without contradiction.

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 two compact sentences that convey purpose, grouping, sorting, linking to aeo_apply, parameter alternatives, and cost. It is front-loaded and every piece of information serves a purpose, with no wasted words.

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 simplicity (2 optional params, no output schema), the description fully explains what it returns (a checklist of improvements with IDs), how to invoke it (audit_id or domain), and how the output relates to sibling tools (aeo_apply). No gaps remain.

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 100% with descriptions for both parameters. The description adds further meaning by clarifying that domain uses the last completed audit and that either audit_id or domain must be provided (mutual exclusivity). This goes beyond the schema alone.

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 returns a checklist of improvements for an audit, grouped by level and sorted by projected gain. It clearly distinguishes from siblings like aeo_apply (which applies improvements) and aeo_audit (which starts an audit), making the purpose unmistakable.

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?

Usage is clearly defined: pass audit_id OR domain (last completed audit). The description also links to aeo_apply, indicating when to use this tool (list) vs that tool (apply). No ambiguity about when to use this tool versus alternatives.

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