Skip to main content
Glama

Draft negotiable quote

draft_negotiable_quote

Generate a priced preview of a B2B quote for human approval, then save it as a draft negotiable quote using the confirmation token; it never submits to the seller.

Instructions

Two-step, human-approved write. Step 1: call WITHOUT confirmation_token to get a priced preview, stock warnings and a confirmation_token. Show the preview to the human and wait for their explicit approval. Step 2: call again with the identical input plus confirmation_token to save it as a DRAFT negotiable quote. This tool never submits the quote to the seller; a person does that in the storefront. Any change to the input needs a new preview.

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": {
      "name": "<name>",
      "lines": "<lines>"
    },
    "name": "draft_negotiable_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesQuote name, e.g. the RFQ reference
linesYes
commentNoMessage to the seller
confirmation_tokenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations mark it as a non-readonly, non-destructive, non-idempotent write; the description goes well beyond that by disclosing the human-approval gate, the token requirement, what Step 1 returns (priced preview, stock warnings, token), and the crucial fact that nothing is submitted to the seller. It also warns that mutating input invalidates the prior preview, which is exactly the kind of non-idempotency context the annotations only hint at.

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?

Four sentences, front-loaded with the write-safety framing and sequenced as Step 1 then Step 2. Every clause carries operational weight; nothing is restated from the name or schema.

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

Completeness5/5

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

With no output schema, the description still tells the agent what Step 1 returns and what Step 2 produces, plus the safety contract around human approval. For a mutating tool with a token handshake, an agent has everything needed to call it correctly in both phases.

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 50%, and the description compensates for the most consequential gap by explaining confirmation_token's origin and the requirement that it accompany identical input. It adds no meaning for name, comment, or line-level note beyond the schema, which keeps this short of a 5.

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?

The description names a specific verb and resource ('draft ... a DRAFT negotiable quote') and immediately bounds the scope by stating 'This tool never submits the quote to the seller.' No sibling tool does anything comparable, and the two-step framing makes the tool's identity unmistakable.

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?

It gives an explicit operating protocol: call without confirmation_token first, show the preview to a human, wait for explicit approval, then re-call with identical input plus the token. It also states the exclusion ('any change to the input needs a new preview') and names the alternative path (a person submits in the storefront), leaving nothing to inference.

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