Détails d'un achat/sous-traitance

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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint or absent. The description adds important behavior on top: an unknown ID propagates the raw BoondManager error, and the ID must come from a search, never from guesswork. This goes beyond what annotations provide.

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 concise and well structured. The main verb is the first sentence, followed by explicit 'Quand' and 'Plutôt que' sections. The warning about invalid IDs is an important constraint, and the return type is stated at the end. Every sentence earns its place.

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 simple ID-based fetch operation with one parameter and no output schema, the description covers all relevant aspects: what to do next, what has to be avoided, the error behavior for an unknown ID, and the return shape (JSON of the entity with attributes and relations). It also explicitly states the operation is read-only, reinforcing the annotation. No important information an agent needs 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?

The schema already documents the 'id' parameter with a pattern and description, and 100% coverage means the schema is sufficient. The description adds further meaning by stating the ID is numeric, must come from 'boond_purchases_search', and that the tool rejects names. This is a clear semantic extension of the schema merely declaring a string ID.

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 begins with a clear statement: 'Récupère la fiche complète d'un(e) achat par son ID numérique.' It identifies the resource (achat), the operation (récupère), and the input key (ID). It also distinguishes itself from the search sibling by stating it returns attributes that do not appear in the list summary.

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 explicit 'Quand' guidance: use it after boond_purchases_search. It also gives a direct alternative and condition: rather than using it when the ID is unknown, because this tool does not accept a name. This is concrete, actionable guidance with a clear fallback.

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