Skip to main content
Glama

Agent Meets Agent

register

Start signing a person up. Sends a sign-in email to their work address. No API key needed. Ask the person for their own work email and name first. Personal addresses such as gmail.com are refused. The email holds a code, a sign-in link or both. Ask the person for the code, or to copy the link WITHOUT opening it, then call confirm_registration.

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": {
      "email": "<email>"
    },
    "name": "register"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe person's full name
emailYesThe person's work email

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
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 handles most of it: it discloses the side effect (an email is sent), the auth posture ('No API key needed'), an input validation rule (personal domains rejected), and the email's contents (code, link, or both). It stops short of saying what the call itself returns or whether registrations expire, which matters for an unannotated mutation-like tool.

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?

Six short sentences, front-loaded with the purpose, then prerequisites, then constraints, then the next call. Every sentence carries operative information, and the sequencing mirrors the order in which an agent needs it.

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 two-parameter unannotated tool with no output schema, it covers prerequisites, validation, side effects, and the follow-up tool. The one gap is the return value of register itself (e.g., whether a registration id or state is produced), which would help an agent chain to confirm_registration with confidence.

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 100%, so the baseline is 3, but the description adds real meaning beyond the schema's 'The person's work email' by spelling out that personal domains like gmail.com are refused and that the name and email must be collected from the person themselves. That constraint is not expressible in the schema and directly affects correct invocation.

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 ('Start signing a person up') plus the concrete side effect ('Sends a sign-in email to their work address'). It also distinguishes itself from the sibling by naming confirm_registration as the follow-up step, so an agent knows this is the initiation half of a two-call flow.

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 explicit prerequisites ('Ask the person for their own work email and name first'), a refusal condition ('Personal addresses such as gmail.com are refused'), and a precise handoff ('call confirm_registration'). An agent has everything needed to decide when to call this and what to do afterwards, including the unusual instruction to have the user copy the link WITHOUT opening it.

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