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

Beyond annotations (readOnlyHint=true, destructiveHint=false), the description discloses detailed async behavior: returns in <300ms, job_id-based polling, ~90s eta, 7-day cache, and webhook callback support. It also lists the exact report structure (7 deliverables) and includes a disclaimer that it is not a substitute for professional legal advice. This is highly transparent about what the tool does and its limitations.

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 dense and information-rich, using a numbered list for output components and clear, actionable sentences. It is longer than typical but every sentence adds essential operational detail (timing, caching, webhook, disclaimer). Minor redundancy such as 'Faster + lighter' and mixing disclaimer at the end does not significantly detract, but a slightly more structured layout would earn a 5.

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 description fully covers the async workflow, including submission, polling, result retrieval, webhook alternative, caching, and expected output format. It also clarifies the legal scope and includes a disclaimer. Given the tool's complexity, this description leaves no critical gaps for an agent to invoke it correctly. The output schema is not needed because the description enumerates the report components.

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 input schema has 100% description coverage for all 7 parameters, so the schema already provides the needed semantics. The description adds contextual value by mentioning that classification is based on Annex III and Article 5, but it does not elaborate on individual parameter meanings or constraints beyond what the schema already states. With full schema coverage, the baseline 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 states the tool audits the EU AI Act, classifies AI systems into risk tiers, and produces a comprehensive report with seven components. It specifies the exact regulation (Règlement UE 2024/1689) and the classification logic (Annexe III, Article 5). It also distinguishes itself from sibling tools by explicitly naming the polling tool (ai_governance_full_report_result) and webhook management (webhooks_manage), clarifying its role as the async submission endpoint.

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 provides explicit usage instructions: it returns a job_id immediately, tells the agent to poll with ai_governance_full_report_result(job_id) after eta_seconds (~90s), and offers an alternative to register a webhook via webhooks_manage. It also notes caching for identical inputs ('Cache 7 jours') and states the webhook path is 'Faster + lighter', guiding the agent to choose the best invocation pattern.

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