Créer un(e) note de frais

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

Annotations are all false, providing little signal, so the description carries the burden. It discloses useful behaviors: creation always goes to 'savedAndNoValidation' state, amountIncludingTax is TTC and tax is a rate with net/VAT recalculated server-side, and the prerequisite dependency. The write nature (readOnlyHint=false) is consistent with a create tool - no contradiction.

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 efficient and front-loaded: purpose first, then the critical prerequisite warning, then line-level semantics, state behavior, and return value. Every sentence earns its place - the 422 warning and TTC/tax clarification prevent real errors. Slightly dense but no wasted prose.

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?

This is a complex create tool (9 top-level params plus a 13-field array), and with all-false annotations, the description must cover cross-cutting concerns. It addresses the external dependency on boond_expenses_default, the TTC/tax recalculation model, and the non-controllable state. Output schema exists so return values are covered. Adequate for the complexity level.

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 coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: the month×resource relationship, that term follows YYYY-MM, that tax is a rate not a mount, that expenseTypeReference comes from boond_expenses_default (not boond_application_dictionary), and that omitting actualExpenses creates an empty report. This adds genuine value.

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 states a specific verb+resource with scope: 'Crée une note de frais dans BoondManager' and adds the defining constraint 'une note de frais = un mois (term) × une ressource'. This clearly distinguishes it from sibling tools like boond_expenses_search, boond_expenses_get, boond_expenses_update, and boond_expenses_delete.

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 prerequisite guidance: 'Appeler boond_expenses_default d'abord' with the named tool and concrete consequence (422 error without it). Context for when to use is clear (creation flow), though it does not explicitly state when not to use it or contrast with update/delete alternatives.

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