Skip to main content
Glama

Outil.io

Link conversation contact

link_conversation_contact

Rattacher la conversation d’un expéditeur hors CRM à un contact (contactId) ou créer la fiche (create). Aucune autorisation marketing n’est cochée.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "threadId": "<threadId>"
    },
    "name": "link_conversation_contact"
  }
}

Input Schema

NameRequiredDescriptionDefault
createNo
threadIdYes
contactIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the agent knows this writes locally. The description adds a genuinely non-obvious behavioral fact: 'Aucune autorisation marketing n'est cochée' — created/linked contacts do not get marketing consent. However, it remains silent on what happens if both contactId and create are supplied, whether an existing contact is overwritten, and whether the operation is reversible.

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?

Two short sentences, front-loaded with the operation and the two-mode choice, with the consent caveat placed last where it belongs. Nothing is redundant, though the omission of threadId means the brevity comes at the cost of coverage rather than being purely economical.

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

Completeness3/5

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

For a mutation tool with a nested object parameter, 0% schema coverage, no output schema, and one required opaque parameter, the description covers the mode choice and consent behavior but leaves the agent guessing about threadId's role and the return value (e.g., whether the resulting contact id is returned). Adequate but with clear gaps.

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

Parameters3/5

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

Schema description coverage is 0%, so the description has to compensate and only partly does: it maps contactId to 'existing contact' and create to 'new contact record', which helps for 2 of 3 parameters. threadId — the one required parameter, with an opaque 64-hex pattern — is never mentioned, and the precedence/conflict rule between contactId and create is left implicit.

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

Purpose4/5

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

The description names a specific verb (rattacher/créer) and resource (conversation, contact) and cleanly splits the two modes: attach to an existing contact via contactId, or create a new record via create. It is not differentiated against a sibling, but the sibling list contains no other contact-linking tool, so the risk of confusion is low. One deduction: the description is in French while the name, title, and annotations are English, which adds a small parsing cost.

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?

Usage context is stated explicitly: a conversation from a sender who is 'hors CRM' (not in the CRM). It also tells the agent which path to take — pass contactId to link an existing contact, use create to make the record. It stops short of stating exclusions (e.g., what to do if the contact already exists, or what to use to attach a conversation that is already in the CRM).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.