Skip to main content
Glama

Atom XII

Ask Atom XII for a quote

request_quote
Idempotent

Send Atom XII a quote request on behalf of a person. Returns an automated acknowledgement and the booking link. Set consent to true only if the person agreed to be contacted. A person on the team answers; nothing is emailed automatically.

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": {
      "need": "<need>",
      "contact": "<contact>",
      "consent": "<consent>",
      "on_behalf_of": "<on_behalf_of>"
    },
    "name": "request_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
needYesWhat the person needs, in their words: the problem, scope, roles or volumes.
testNoTrue to test an integration: recorded and marked as a test, nobody follows up.
agentNoThe agent sending this (optional but recommended). The User-Agent header is recorded too.
budgetNoBudget or range, free text (e.g. "$20k-30k a month").
companyNoThe organization the person represents.
consentYesTrue only if the person named in contact agreed to be contacted by this company about this inquiry.
contactYesThe person to answer. An email or a phone is required.
languageNoLanguage for the answer.
timelineNoWhen they want to start or decide.
on_behalf_ofYesWho the agent acts for: the person and, if any, their organization.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

The annotations already declare that this writes data (readOnlyHint false, destructiveHint false, idempotent true), so the bar for disclosure is lower. Even so, the description still earns credit: it says what comes back (an automated acknowledgement plus a booking link) and it says that no automated email is sent, and that a person on the team answers. It does not say whether rate limits or login requirements exist, or how long a human reply usually takes.

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?

Four short sentences, and the key framing — who the request is from and what happens next — comes first. The consent sentence is correctly placed next to the action, for clarity. There is 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?

This tool has 10 parameters, including nested objects such as contact and agent, and there is no output schema, so the description has to explain the return path; it does so, with the acknowledgement and the booking link. What is missing is how long a human reply takes and what 'test' mode does. That is a minor gap because the schema documents test.

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 100%, so every parameter is already documented in the schema. The description only restates the consent precondition, and that precondition is already present in the consent field's own description. This is adequate, but it adds no syntax or format details.

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?

Opens with a specific verb and resource: 'Send Atom XII a quote request on behalf of a person.' That is unmistakably distinct from book_call and get_pricing. It never explicitly says how it differs from send_inquiry, though, so the sibling differentiation is implied rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives one concrete precondition: set consent to true only if the person agreed to be contacted. Beyond that, there is no guidance on when to pick this over send_inquiry, or what to do when the request is for general information rather than a quote. It is enough for an agent to infer the use case, nothing more.

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.

Resources