Skip to main content
Glama

Outil.io

Send letter

send_letter
Destructive

Courrier postal (lettre ou plaquette PDF) imprimé et posté par La Poste via le compte Merci Facteur Pro DU CLIENT. Par défaut send:false = devis seulement (prix) ; send:true envoie réellement et débite son compte : uniquement après accord explicite du client sur le prix. recipient {nom|societe, adresse1, cp, ville, pays}, pdfUrls https (1 à 10), mode normal (lettre verte) | suivi | lrar, printSides recto|rectoverso, pages, requestId stable (anti-doublon 30 jours). Devis Outil par la poste : pdfUrls=[pdfUrl de get_quote] (PDF figé, ne pas le régénérer). L’envoi est inscrit sur la fiche (log_activity kind letter). Sans compte connecté, la réponse dit exactement quoi fournir.

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": {
      "recipient": "<recipient>",
      "pdfUrls": "<pdfUrls>",
      "requestId": "<requestId>"
    },
    "name": "send_letter"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo
sendNo
pagesNo
senderNo
pdfUrlsYes
contactIdNo
recipientYes
requestIdYes
printSidesNo
prospectIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint and openWorldHint, but the description adds real substance beyond them: a financial debit on the client's account, the hard precondition of explicit price approval, a 30-day anti-duplicate window keyed on requestId, the fact that the frozen quote PDF must not be regenerated, and an audit trail via log_activity kind letter. Only the exact response shape is left unclear, which keeps it just under 5.

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?

Purpose is front-loaded and the highest-risk fact (default send:false, debit on send:true) follows immediately. The semicolon-dense parameter run is information-rich rather than padded, though the compression makes it slightly harder to scan.

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 10-parameter, nested, destructive, no-output-schema tool, the description covers the mutation, the cost, the approval precondition, idempotency, and the fallback when no account is connected. Return-value details and the role of the optional contactId/prospectId link fields are the remaining gaps.

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 0%, so the description must compensate and largely does: it names the recipient fields, the https/1-to-10 pdfUrls constraint, the mode enum (normal/suivi/lrar), printSides (recto/rectoverso), pages, and the meaning of the requestId stability window. contactId, prospectId, and sender are left undocumented in both places.

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 — postal mail (letter or PDF flyer) printed and posted by La Poste through the client's own Merci Facteur Pro account — with an explicit scope distinction: with send:false this tool is only a quote, the real mailing being done via get_quote's frozen PDF. An agent can separate it from the send_* siblings without opening any schema.

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?

Gives the exact conditional: send:false (default) produces a price quote, send:true actually mails and debits the account, and that must only be triggered after the client explicitly agrees to the price. It also routes the quote path to the sibling (pdfUrls=[pdfUrl from get_quote]) and covers the no-connected-account case.

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.