Modifier un positionnement

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context beyond annotations: it explains that only provided fields are modified ('Seuls les champs fournis sont modifiés'), that startDate/endDate can be cleared with an empty string, and that stateReasonTypeOf/stateReasonDetail are folded into a stateReason object. These details are not present in annotations and enhance understanding. No contradiction 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 well-structured with a clear opening statement of function and endpoint, followed by explicit usage conditions ('Quand', 'Plutôt que'), and a concise argument list. Every sentence serves a purpose; nothing is fluff. The structure front-loads the key differentiator (update vs create) and minimizes redundancy.

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?

The description covers all necessary aspects: it names the HTTP method and endpoint, specifies the partial-update behavior, provides explicit usage conditions, explains how to clear date fields, groups related parameters, and states the return type ('Données mises à jour du positionnement'). Since an output schema exists, return details are not required. The description is complete for an agent to invoke the tool correctly.

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 description coverage is 100% (all 7 params have descriptions), so the baseline is 3. However, the description adds meaningful semantic clarity beyond the schema: it groups stateReasonTypeOf and stateReasonDetail to be sent as a nested stateReason object, clarifies that startDate/endDate empty strings clear the values, and specifies the max length for informationComments. This extra context helps the agent construct correct calls.

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 updates an existing positioning ('Met à jour un positionnement existant') and includes the HTTP endpoint PUT /positionings/{id}. It explicitly differentiates from the sibling `boond_positionings_create` by saying 'Plutôt que : boond_positionings_create si le positionnement n'existe pas encore', which enables correct sibling selection.

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 an explicit 'Quand' condition ('pour faire avancer l'état d'un positionnement (proposé → retenu → refusé)') and an explicit 'Plutôt que' alternative ('boond_positionings_create si le positionnement n'existe pas encore'). This gives clear when and when-not guidance, fully meeting the usage criteria.

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