Skip to main content
Glama

Constat Auto — Constat amiable

by io.github.Doran56

constat_renseigner

DestructiveIdempotent

Enregistre ou met à jour les informations du constat. Appelez-le autant de fois que nécessaire, par petits groupes de champs, au fil de la conversation. Seuls les champs fournis sont modifiés. N'inventez jamais une valeur : un champ inconnu doit rester absent. Attention : modifier un constat déjà signé invalide les signatures et oblige à solliciter de nouveau les conducteurs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dossierYesIdentifiant du dossier renvoyé par constat_demarrer.
accidentNoCirconstances de temps et de lieu de l'accident.
conducteur_aNoVéhicule A : celui de la personne à qui vous parlez. Ne remplir que les champs connus, et n'inventer aucune valeur — un champ inconnu doit rester absent.
conducteur_bNoVéhicule B : l'autre véhicule impliqué. Mêmes champs que conducteur_a.
destinataireNoAssureur ou courtier à qui le constat signé sera transmis.
observations_aNoObservations du conducteur A, dans ses propres mots.
observations_bNoObservations du conducteur B, si elles ont été recueillies.
circonstances_aNoNuméros des cases de circonstances cochées pour A, de 1 à 17. Appeler constat_circonstances pour la liste officielle et relire les cases au conducteur.
circonstances_bNoNuméros des cases de circonstances cochées pour B, de 1 à 17.
conducteur_b_absentNotrue si le second conducteur n'a pas pu être identifié (délit de fuite, véhicule stationné sans propriétaire présent). Le constat est alors une déclaration unilatérale.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds crucial context beyond those: only provided fields are modified ('Seuls les champs fournis sont modifiés'), a strict no-invention policy discourages open-world assumptions, and modifying a signed constat invalidates signatures. These behavioral traits align with the annotations and add significant value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences. The first states the purpose, the second explains the incremental calling pattern and field update rule, and the third warns about signed records. No redundancy, no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (nested objects, 10 parameters, no output schema), the description covers the essential behavioral contract: partial updates, no invented values, and signature invalidation. It omits explicit cross-references to constat_demarrer for obtaining the dossier ID, but that is available in the schema. The description is sufficient for an agent to use the tool correctly within the workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description elevates this by explaining partial-update semantics: 'Seuls les champs fournis sont modifiés' tells the agent that calling with a subset of fields won't clobber others. The instruction 'un champ inconnu doit rester absent' reinforces the closed-world behavior, which is not explicit in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Enregistre ou met à jour les informations du constat' (records/updates accident report info). It clearly distinguishes this tool from siblings like constat_demarrer (start) and constat_finaliser (finalize) by emphasizing incremental data entry and repeated calls.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly instructs when to invoke: 'Appelez-le autant de fois que nécessaire, par petits groupes de champs, au fil de la conversation' – call it as often as needed, in small field groups. It also warns about modifying signed constats. However, it doesn't explicitly name alternative tools for starting/finalizing, though context signals make the usage clear.

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

All Constat Auto — Constat amiable toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

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.

Naming Consistency3/5

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.

Tool Count5/5

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.

Completeness4/5

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.

Resources