Skip to main content
Glama

Outil.io

List replies

list_replies
Read-only

Réponses des prospects, les plus récentes d’abord : e-mail lu dans la boîte du client par IMAP (toutes les 5 min), WhatsApp, Telegram, SMS, formulaires, et réponses LinkedIn/Instagram inscrites par report_reply. Chaque réponse porte prospectId/contactId, le texte et l’intention (interested, later, not_interested, stop, question, unclassified). unhandled:true = pas encore traitées ; après avoir répondu, set_reply_intent avec handled:true.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_replies"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
sinceNo
intentNo
contactIdNo
unhandledNo
outreachIdNo
prospectIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description still adds meaningful behavior: freshness/latency (email ingested via IMAP every 5 min), ordering (newest first), the fact that LinkedIn/Instagram items exist only when written by report_reply, and the handled/unhandled lifecycle. That is the kind of context annotations cannot carry.

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?

Three dense sentences, front-loaded with the resource and ordering, then sources, then the payload fields, then the workflow hint — no filler. It is information-dense to the point of slight crowding, but every clause (including the IMAP polling interval) earns its place.

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?

For a read-only list tool with no output schema, it discloses the returned fields (prospectId/contactId, text, intent), ordering, source coverage, and the handled lifecycle, which is what an agent needs to call and interpret it. The remaining gap is pagination/windowing behavior (limit, since) and whether results are scoped to an account.

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% across 7 params, so the description carries the burden: it gives real semantics for unhandled ('not yet processed') and names the intent domain with its meanings, and the id filters are largely self-describing. However, limit, since (no format or timezone given), and outreachId are left entirely to inference, so compensation is partial.

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?

States a specific verb and resource ('Réponses des prospects' listed most-recent-first) plus the full source set (IMAP, WhatsApp, Telegram, SMS, forms, LinkedIn/Instagram via report_reply), which lets an agent distinguish it from list_* siblings and from report_reply/set_reply_intent. The purpose is unambiguous without opening the schema.

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 concrete workflow routing: 'unhandled:true = pas encore traitées' tells the agent which filter to use for pending work, and 'après avoir répondu, set_reply_intent avec handled:true' names the follow-up tool and the condition that selects it. It stops short of an explicit when-not-to-use statement or pointing at a broader activity listing tool.

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.