Modifier un(e) note de frais

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

The description adds behavioral context beyond annotations by stating that only provided fields are modified and that it returns updated data. It does not contradict the annotations (idempotentHint=true, readOnlyHint=false). However, it does not warn about the destructive replacement of actualExpenses, which is a notable behavior, though that detail is present in the schema.

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 extremely concise (two sentences) with no fluff. It states the action, the partial-update behavior, and the return value in a clear and direct manner, achieving high efficiency.

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?

Despite a rich schema, the description is too sparse to be complete for a complex tool. It omits crucial usage context such as the behavior of actualExpenses (replacing all lines) and the need to obtain the full list of lines before adding new ones. The schema contains these details, but the description does not summarize them for the agent, leaving the tool potentially misused.

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 description coverage is 100%, so the baseline is 3. The tool description does not add any parameter-specific semantics beyond the generic partial-update note, which applies to all parameters equally. It does not explain any parameter interactions or special cases.

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 expense report ('Met à jour un(e) note de frais existant(e)'), with a clear verb and resource. It distinguishes from siblings like create, delete, get, and search by specifying the update operation.

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 does not explicitly state when to use this tool versus alternatives. It lacks guidance such as 'use create for new reports' or the need to first retrieve the report via get before adding lines because actualExpenses replaces all lines. The partial update note ('Seuls les champs fournis sont modifiés') is a behavior, not a usage guideline.

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