Modifier un achat/sous-traitance

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false. The description adds important behavioral context: partial update semantics (only provided fields are written), table fields are replaced not merged, and the use of rights check to avoid 403. It doesn't cover edge cases like what happens if the ID doesn't exist, but given the annotations, this is a minor gap. 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 sections for 'Quand', 'Plutôt que', key behavioral notes, and a returns statement. It is front-loaded with the purpose. A minor inefficiency: the section on table fields could be more concise (e.g., 'array fields are replaced, not merged'), but overall it's clear and to the point.

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 the tool's complexity (15 parameters, partial update semantics) and the presence of an output schema, the description covers the essential aspects: partial update, array replacement, and rights check. It does not mention whether all fields are optional beyond 'id' (implied by partial update), or what happens on invalid input, but the tool is a standard update operation and the output schema handles return format. A 4 is appropriate.

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%, so parameters are well-documented in the schema. The description adds a general note about partial update (only provided fields are written) which is helpful for all parameters, and specifically warns about array fields being replaced. However, it doesn't detail each parameter beyond what the schema provides, so it meets the baseline of 3.

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 it updates an existing purchase identified by ID, with a specific verb and resource. It distinguishes from sibling `boond_purchases_create` by explicitly saying 'Plutôt que' and specifying the condition (if the record doesn't exist yet). It also mentions partial update and table fields behavior, making the tool's functionality unmistakable.

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?

It provides a clear 'Quand' (when to use) and 'Plutôt que' (instead of) section, explicitly naming the alternative `boond_purchases_create` and the condition for choosing it. It also advises checking `boond_rights_get` to avoid a 403, which is additional usage guidance. This is exemplary.

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