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

The annotations already mark the tool as read-only and non-destructive. The description adds that the data originates from 'Projet Ariane', which gives context about the data source. It also specifies that results include links to detailed sheets, but it does not disclose potential variations in result counts or whether results are exhaustive. Given the annotations, the description adds useful context, so a 4 is appropriate.

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 a single, dense sentence that packs in the key information: what is searched (schools by various criteria), the example results (campuses, number of formations), and the data source (Projet Ariane). There is no redundancy or fluff; every phrase contributes to clarity. This is well-structured and front-loaded with the main verb.

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 moderate complexity (3 parameters, all documented in schema) and no output schema, the description is quite complete: it explains the search scope, what results include, and cites the data source. It does not explain the structure of return values, but without an output schema, that may not be strictly necessary. The only minor gap is not mentioning result ordering or pagination, but that is not critical for a search tool.

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 schema covers all parameters with descriptions (100% coverage), so the description doesn't need to add much. The description does mention 'campus' and 'formations' which align with the parameters but doesn't add deeper semantics like example formats or value constraints beyond the schema. Since schema coverage is high, the baseline is 3, and the description adds marginal value.

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's purpose: finding schools and institutions by various criteria (name, acronym, city, type), and it specifies the types included (universities, engineering schools, etc.). It also mentions the results include campuses, number of programs, and links to detailed sheets, which adds specificity. This distinguishes it from siblings like 'rechercher_formation' and 'rechercher_metier'.

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 clear context on how to use the tool: search by name, acronym, city, or type, and the output includes campuses, number of formations, and links. However, it does not explicitly state when not to use this tool or mention alternative tools like 'ou_se_former' or 'fiche_ecole', which might serve similar purposes. The exclusion of alternatives is a minor gap.

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