fixou

create_request

Cree une demande de devis Fixou au nom du client final. IMPORTANT : la demande n'est PAS publiee immediatement — elle attend une confirmation par email (double opt-in). L'email est celui du CLIENT FINAL (pas de l'agent) et est obligatoire : le client recevra un email « Confirmez votre demande » avec un lien valable 48 heures ; tant qu'il n'a pas clique, aucun artisan n'est contacte. Apres cet appel, invitez explicitement l'utilisateur a ouvrir sa boite mail et a cliquer sur ce lien de confirmation pour publier sa demande et suivre les reponses sur fixou.fr ; l'agent lui-meme n'a jamais acces a cet espace. La description doit faire au moins 20 caracteres. answers reprend les id de questions et les value d'options du metier (voir list_categories). Renvoie le requestId a utiliser avec get_request.

Input Schema

TableJSON Schema

Name	Required	Description
`email`	Yes	Email du client final (obligatoire) ; il y recevra le lien de confirmation a cliquer pour publier sa demande, puis le suivi.
`phone`	No	Telephone du client final (optionnel), transmis aux artisans qu'il choisira.
`answers`	Yes	Reponses au questionnaire du metier, indexees par `id` de question. Valeur unique (question single) ou tableau de valeurs (question multi), choisies parmi les `value` des options.
`postalCode`	Yes	Code postal francais du lieu d'intervention (5 chiffres).
`description`	Yes	Description libre du besoin, en francais, de 20 a 5000 caracteres.
`categorySlug`	Yes	Slug du metier concerne, obtenu via list_categories.

TDQS

A4.8/5.0

Behavior5/5

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

Discloses critical behaviors: request is not published immediately, requires email confirmation (double opt-in), link expires in 48 hours, email is client's not agent's. No annotations to contradict.

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

Conciseness4/5

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

Description is relatively long but well-structured: purpose, caveat, email details, post-call instructions, parameter notes. Each sentence adds value; could be slightly more concise but acceptable.

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

Completeness5/5

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

With no output schema, description mentions returning requestId for use with get_request. Covers min description length, answers format from list_categories, and workflow end-to-end. Very complete.

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. Description adds meaning by explaining the workflow for answers and email, e.g., 'answers reprend les id de questions et les value d options'. Adds above baseline.

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 clearly states the tool creates a quote request for Fixou on behalf of the client. It distinguishes itself from siblings by detailing the double opt-in process and referencing get_request and list_categories.

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

Usage Guidelines5/5

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

Explicitly advises the agent to invite the user to check email and click the confirmation link after the call. States the agent never accesses the client space, providing clear context for when to use.

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

All fixou tools Inspect

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

A4.6/5.0

Disambiguation5/5

Each tool targets a distinct operation: creating a request, retrieving its status, and listing categories. There is no overlap in functionality, making it clear which tool to use for each action.

Naming Consistency5/5

All tools use a consistent verb_noun pattern in snake_case (create_request, get_request, list_categories), making the naming predictable and easy to understand.

Tool Count5/5

With 3 tools, the server is well-scoped for its purpose of managing quote requests. The number is not excessive and each tool serves a necessary function without redundancy.

Completeness3/5

The server covers creation and retrieval of requests, and listing categories, but lacks tools for listing all requests created by an agent, updating a request, or deleting a request. These gaps could hinder streamlined workflows.

Resources

Need Help?