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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real context beyond annotations: the corpus size ("plus de 2 000 concerts"), geographic coverage, and the returned fields (date, heure, titre, salle, ville, lien, billetterie). It does not discuss pagination behavior or how the limite cap interacts with result volume, which keeps it from a 5.

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 sentences, front-loaded with the resource and scope, then the flexibility of the criteria, then the return shape. Dense but every sentence carries information. Slightly crowded by the long parenthetical list of regions.

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?

With no output schema, the description correctly compensates by enumerating the returned fields (date, heure, titre, salle, ville, liens). It also explains that all 9 parameters are optional and combinable, matching the 0-required schema. Minor gaps remain around result limits and ordering, but nothing essential to a correct call is missing.

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 67%, so most parameters are self-documented. The description's examples implicitly illustrate combinable filters (salle + date, categorie + ville + date, festival name), which adds some meaning beyond the schema. But the two enum parameters (pays, categorie) and the limite cap get no elaboration in the description, so it only marginally compensates for the coverage gap.

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 and resource ("Recherche dans l'Agenda Crescendo") plus a concrete scope: 2000+ classical concerts in Belgium and the Eurorégion. This clearly separates it from chercher_compositeurs, disques_crescendo and fiche_compositeur. However, it never contrasts itself with prochains_concerts, which is the most closely overlapping sibling, so sibling differentiation is incomplete.

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 line "Tous les critères sont facultatifs et combinables" with three worked example queries ("que joue Flagey en novembre", "opéra à Liège ce mois-ci") gives useful implied guidance on how to combine filters. But there is no explicit when-to-use vs when-not, and the near-identical sibling prochains_concerts is never mentioned as an alternative.

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