Skip to main content
Glama
Sign In

Outil.io

by io.outil
OverviewDiscussionsAdmin

Queue outreach messages

queue_outreach_messages

Mettre en file jusqu’à 100 premiers messages personnalisés (linkedin, facebook, instagram, tiktok, whatsapp). mode validation : chaque message attend l’accord du client ; auto : pris en charge par MonAssocié sans validation dans le plafond quotidien par réseau. Pas de second message à la même personne avant 30 jours ; WhatsApp seulement vers des contacts consentants.

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": {
      "items": "<items>"
    },
    "name": "queue_outreach_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo
itemsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only say the tool is a non-read-only, non-destructive, closed-world write. The description adds much more: a 100-message batch ceiling, two execution modes with different approval behavior, a 30-day per-recipient cooldown, and a WhatsApp consent requirement. It does not describe rate-limit errors or what happens to partially rejected batches.

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?

A dense, front-loaded paragraph: the verb and the 100-message cap come first, then the mode semantics, then the rules. No filler, though it is written in French while the tool name, title, and annotations are English, which adds a translation step for the agent.

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 queuing tool with a complex nested items array and no output schema, the description should say what results look like (queued count, per-item errors) and how contactId/prospectId interact with recipientUrl. Those gaps remain, though the operationally critical constraints are covered.

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 must carry the parameters. It does a good job on mode (validation vs auto, daily cap per network) and on the items cap and platform set, but it never explains recipientUrl vs contactId/prospectId/recipientName, or the attachments sub-structure (max 4, image/video/document).

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?

States a specific verb and resource ('Mettre en file ... messages personnalisés') along with the concrete scope: up to 100 messages, and the five supported platforms. It does not name sibling tools (for example approve_outreach_messages), but the validation/auto modes implicitly separate queuing from approval.

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?

Gives real conditions for use: validation mode waits for client approval, while auto mode is handled by MonAssocié within the daily per-network cap. It also states constraints (no second message to the same person for 30 days; WhatsApp only for consenting contacts). It does not name an alternative tool or say when not to use this one.

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

All Outil.io toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources