Skip to main content
Glama

draft_message

Draft an opening offer, reply, or follow-up message to the seller for buyer review and confirmation before sending.

Instructions

Prepare a message to the seller (opening offer, answer or follow-up) for the buyer to confirm. Nothing is sent. Show the buyer the draft and ask whether to send or change it. If they want changes, call this again with the new text and their words as feedback. The server refuses drafts that break the rules and says why.

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": {
      "negotiation_id": "<negotiation_id>",
      "message": "<message>"
    },
    "name": "draft_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYesThe text for the seller, in German
feedbackNoWhen revising: what the buyer asked to change, in their words
offer_eurNoSet whenever the message names a price you offer
negotiation_idYesNegotiation id from start_negotiation / list_negotiations

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the key non-side-effect ('Nothing is sent'), the human-in-the-loop confirmation requirement, the revision loop via feedback, and that server-side validation rejects rule-breaking drafts with an explanation. It omits whether the draft is persisted, whether negotiation state changes, and what the response looks like.

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

Conciseness5/5

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

Front-loaded with the purpose, then side-effect, then the confirmation/revision protocol; each of the four short sentences adds distinct operational information with no filler.

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 4-parameter mutation tool with no annotations and no output schema, the description covers the critical unknowns: nothing is sent, the buyer must confirm, revisions reuse the same tool, and invalid drafts fail loudly with a reason. Return-shape details are the only notable gap.

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 coverage is 100%, so message, feedback, offer_eur and negotiation_id are already documented in the schema. The description only restates the feedback concept ('their words as feedback') and says nothing about offer_eur or the id source, so baseline 3 applies.

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 ('Prepare a message to the seller') and enumerates the covered cases (opening offer, answer, follow-up). The sentence 'Nothing is sent' implicitly distinguishes it from send_draft, so an agent can tell the prepare step from the send step without opening another 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 a clear workflow: show the draft to the buyer, ask whether to send or change, and re-call with the new text plus the buyer's words as feedback. It never names send_draft or discard_draft explicitly as the follow-up tools, and gives no exclusions, so it stops short of full alternative routing.

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