Créer un contrat

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

The description explicitly discloses non-idempotency ('deux appels identiques créent deux contrats'), which aligns with and adds context beyond the idempotentHint=false annotation. It also adds practical behavioral details about the typeOf dictionary ID requirement and the location of the created contract's ID in structuredContent.id.

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 and economical: a one-line purpose, clear 'when' and 'alternative' sections, two focused bullets, and a returns note. Every sentence adds actionable information without 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?

With no output schema, the description usefully explains the return value and where to find the new ID. It covers the main usage context, the key non-idempotency warning, and the dictionary type pitfall. A small gap is that required parameters are not explicitly clarified, but the schema lists 0 required and the description otherwise gives sufficient context for correct invocation.

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 important semantic value by clarifying that typeOf is an integer dictionary ID from boond://dictionary/typeOf/contracts, not a label, which is a key disambiguation beyond the schema's generic description.

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 opens with a specific verb and resource: 'Crée un contrat de travail rattaché à une ressource.' It clearly identifies the action and its object, and distinguishes itself from the sibling tools boond_contracts_search and boond_contracts_get.

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 'Quand' section explicitly states when to use the tool: to register a new contract (embauche, avenant, renouvellement). The 'Plutôt que' section names an exact alternative, boond_contracts_search, and instructs the agent to check for overlapping contracts first, providing clear decision guidance.

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