Deviner le code ROME d'un intitulé (IA)

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

Annotations already mark the tool as readOnly, openWorld, idempotent, and non-destructive. The description adds important behavioral context: it returns predictions sorted by score, requires an API subscription ('Nécessite l'abonnement à l'API « ROMEO 2 »'), and allows adjusting thresholds. No contradictions with annotations.

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 two concise paragraphs, front-loaded with the verb and resource in the first sentence. Every sentence adds value: purpose, use with siblings, output behavior, threshold guidance, and subscription requirement. No wasted words.

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 no output schema, the description explains the return format (predictions sorted by score). It covers the required subscription, parameter guidance (seuilScore), and the primary use case. It is sufficiently complete for a prediction tool of moderate complexity, though it could mention pagination or error handling.

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 describes 3 of 4 parameters (75% coverage). The description adds usage guidance for seuilScore ('Ajustez … pour ne garder que les prédictions fiables') but does not significantly enhance the semantic meaning of intitule or nbResultats beyond the schema. Baseline 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 starts with a specific verb ('Utilise ROMEO 2 pour rapprocher') and clearly states the resource (intitulé to ROME codes). It distinguishes from siblings by explicitly offering to convert free text into codes usable by ft_search_offres and ft_search_entreprises, which no other sibling tool does.

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 gives clear context: 'C'est le meilleur moyen de convertir … en code ROME exploitable par ft_search_offres et ft_search_entreprises.' It also advises adjusting seuilScore for reliability. Although it does not explicitly list when not to use it, the sibling tools are sufficiently different (get_offre, search_metiers) that the main use case is unambiguous.

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