Ouvre un dossier de constat amiable et renvoie son identifiant, à réutiliser dans tous les appels suivants. À appeler une seule fois au début de la conversation. Renvoie aussi la liste des informations à recueillir.
| Name | Required | Description | Default |
|---|---|---|---|
| langue | No | Langue du constat et des liens de signature. Par défaut fr. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even though annotations are present (all false), they provide limited safety context. The description adds behavioral details beyond annotations: the tool creates a new dossier, returns an identifier to reuse, and also returns a list of information to collect. It also warns that it should be called only once, implying non-idempotent behavior, which is valuable transparency.
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 concise and well-structured: three sentences each serving a distinct purpose (what it does, when to use it, what it also returns). There is no filler or redundancy, and key information is front-loaded.
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 having no output schema, the description adequately explains the tool's outputs (identifier and list of info) and its role in the conversation flow. It covers the essential context for an initialization tool: what it returns, how to use the returned ID, and that it is the first step. The single optional parameter is fully documented in the schema.
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 input schema fully covers the only parameter 'langue' with a description ('Langue du constat et des liens de signature. Par défaut fr.'). The tool description adds no additional parameter meaning, so the baseline of 3 applies given the high schema coverage.
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's action ('Ouvre un dossier de constat amiable') and its primary output ('renvoie son identifiant'). It distinguishes itself from sibling tools by being the initialization step in the workflow, even mentioning that the returned ID should be reused in all subsequent calls.
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 timing guidance: 'À appeler une seule fois au début de la conversation.' It implies the tool is the entry point and should not be repeated, which is clear contextual usage. It does not explicitly name alternatives, but the role as the starting step is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each constat_* tool corresponds to a distinct phase of the accident statement workflow—starting, filling, sketching, signing, status checking, finalizing, canceling—with no two tools overlapping in purpose. The two guide-related tools (search, fetch) are clearly separate from the workflow tools.
The constat_ prefix provides a recognizable pattern, but the suffix alternates between verbs (demarrer, renseigner, finaliser, annuler) and nouns (circonstances, croquis, signatures, statut, assureurs). Additionally, the two guide tools (fetch, search) break the pattern entirely, mixing languages and conventions.
With 11 tools, the server is well-scoped for its purpose: each tool serves a clear step in the constat process and the two guide tools complement the primary workflow without redundancy. The count is within the ideal 3–15 range and does not feel heavy or thin.
The workflow is well covered: start, fill, sketch, sign, monitor status, finalize, and cancel. A minor gap is the lack of a dedicated 'get full constat contents' tool (statut only shows missing fields and signature state), but the core lifecycle is otherwise complete.
