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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the fiche is read by official UAI code and 'chaque donnée est accompagnée de sa source et de son année', which tells the agent about data provenance and freshness.

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?

Three tight sentences, purpose front-loaded, followed by input sourcing and a data-provenance note. No padding; each sentence carries information, though the final sentence is a minor add-on.

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?

For a single-parameter read tool with rich annotations and no output schema, the description covers both the input (how to obtain the UAI) and the output shape (the field groups returned). Nothing essential is missing, though error behavior for an unknown UAI is unaddressed.

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% and the pattern is documented, so baseline is 3. The description goes beyond the schema by explaining where the UAI comes from (the search tool's results) and giving a concrete example (0350760L), which helps an agent obtain a valid 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?

States a specific verb ('Présente la fiche') and resource ('établissement'), then enumerates exactly what the record contains (identité, coordonnées, dispositifs, effectifs, résultats, IPS, lettre de notation). This clearly distinguishes it from trouver_etablissement (search) and secteur_d_une_adresse (address lookup).

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 implied rather than stated: by noting the UAI is 'le code officiel que l'outil de recherche donne pour chaque résultat', it hints the tool follows a search. However, no sibling is named, and there is no explicit when-to-use/when-not guidance for choosing between it and trouver_etablissement.

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