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

Annotations already cover safety (readOnlyHint, idempotentHint, non-destructive), so the bar is appropriately lower. The description adds meaningful context: it clarifies that no personal data is required, no formation-specific figures are provided, and that official verification is the user's responsibility—going beyond what annotations convey.

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 front-loaded with relatable example questions that immediately orient the reader, followed by a concise explanation of what the tool provides and its limitations. It is slightly long but every sentence earns its place by clarifying purpose, scope, and constraints.

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 a single required enum parameter, rich annotations, and an output schema, the description is nearly complete. It covers what the tool does, what it does not do, and the expected data-handling stance. The only minor gap is that it does not explicitly differentiate from sibling tools by name, but the context is otherwise sufficient for correct invocation.

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 an enum of 21 values, so the schema already documents the parameter thoroughly. The description adds value by framing what the 'sujet' represents (the person's need) and explicitly noting that the raw question and personal data should not be transmitted, complementing rather than repeating the schema.

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 conveys a specific purpose: explaining orientation questions and pointing to relevant pages, with a clear intent to explain rather than evaluate. It distinguishes itself from data-lookup siblings (lire_formation, comparer_formations) by explicitly stating it does not evaluate a dossier or predict admission, though it does not name those siblings directly.

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 the categories of topics handled (choix, comparaison, accès, réussite, etc.), providing an implicit sense of when to use the tool, but it does not explicitly state when not to use it or name alternative tools for distinct needs. The negative constraints (no dossier, no admission prediction) provide some boundary guidance.

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