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

Annotations already declare readOnlyHint=true, and the description adds valuable behavioral context: the derived basis meaning (denominator reconstructed from old scans making the rate a floor), the null share_of_voice when no competitors are tracked (explicitly stating it's not 0), the requirement for IA Monitoring, and that the tool is free. No contradictions with annotations.

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 efficient, front-loading the core purpose and then adding details about output fields and prerequisites. It avoids unnecessary elaboration, though it could slightly benefit from removing the parenthetical 'voir caveat' without context. Overall, it earns its space.

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 no output schema, the description explains key fields (basis, share_of_voice) but does not fully document the return structure (e.g., date format, engine list, caveat content). It is adequate for a simple query tool but leaves some ambiguity for an AI agent with no output schema.

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 single parameter 'domain' has schema coverage 100% with a clear description 'domaine à inspecter'. The description does not add new semantic information beyond what the schema already provides, so the baseline score of 3 is appropriate.

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 specifies the verb ('Historique de citation') and resource ('domaine'), listing the exact output metrics (taux de citation par date, détail par moteur, part de voix). These details help differentiate it from sibling tools like aeo_apply, aeo_audit, or aeo_report, which have different purposes.

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 mentions a prerequisite ('Nécessite un Monitoring IA sur ce domaine') but provides no guidance on when to use this tool versus alternatives (e.g., when to use aeo_report instead, or when not to use it). No explicit when-not-to-use or comparison with siblings is given.

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