Skip to main content
Glama

Tommos

Remove a person's link to a company

remove_the_link_of_a_person
DestructiveIdempotent

Take a person's link to a company by hand off, as the signed-in person, as the person's page does. The rule of the mail domain applies again at once: the answer names the company the domain of their mail gives them now, or none (a free-mail address, one of the workspace's own). Refused when the person belongs by the domain of their mail, or has no company. The removal is a line of the company's history and of the audit trail.

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": {
      "contact_id": "<contact_id>"
    },
    "name": "remove_the_link_of_a_person"
  }
}

Input Schema

NameRequiredDescriptionDefault
contact_idYesThe person's contact id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, idempotentHint=true and readOnlyHint=false, so safety is covered. The description adds real value beyond that: it names the refusal conditions, states the post-condition (the answer names the company the mail domain now implies, or none), and discloses that the removal is recorded in company history and the audit trail. Only the 'as the signed-in person' authorization model is loosely sketched.

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

Conciseness3/5

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

The description is short and front-loads the action, but several phrases are opaque ('by hand off', 'The rule of the mail domain applies again at once'), and the final sentence about history/audit trail is buried. Signal is present but packaging costs the reader effort.

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 one-parameter destructive mutation with no output schema, the description covers refusal conditions, the resulting domain-based classification, and the audit/history side effect — enough for an agent to decide and call safely. Minor gap: no confirmation that a contact_id must exist or what error looks like, though the refusal cases partly compensate.

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% for the single contact_id parameter, so the schema carries the parameter documentation. The description adds no format or source hints for contact_id, which is acceptable at baseline but not beyond it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description does convey the core action — removing a person's link to a company — and implies the inverse of sibling link_a_person_to_a_company. But the phrasing is convoluted ('Take a person's link to a company by hand off, as the signed-in person, as the person's page does'), so an agent must decode rather than read the purpose directly. A specific verb and resource are present, but sibling differentiation is only implicit.

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?

Useful constraints are given: it is refused when the person belongs via their mail domain or has no company, which effectively states when the tool will fail. However, there is no explicit guidance on when to pick this over alternatives (e.g. the inverse link tool), and the refusal conditions are behavioral limits rather than selection guidance.

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.