Skip to main content
Glama

Unrelate repositories

unrelate_repositories
Destructive

Stop AI code reviews relating two repositories: removes the stated relationship between them under one GitHub App installation, in whichever order each was stated. Organisation admins only. Reviews already posted do not change, and this cannot unrelate applications installed on the same cluster - those are related with nothing stated. list_related_repositories shows what is stated.

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": {
      "installation_id": "<installation_id>",
      "repository": "<repository>",
      "related_repository": "<related_repository>"
    },
    "name": "unrelate_repositories"
  }
}

Input Schema

NameRequiredDescriptionDefault
repositoryYesRepository path, owner/name.
installation_idYesNumeric id of the GitHub App installation the relationship belongs to, as a string. list_credentials with provider github reports installation_id for every GitHub App credential.
related_repositoryYesThe other repository, owner/name. The relationship is symmetric, so which one is which does not matter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real context beyond them: posted reviews are unaffected, the operation is installation-scoped, and implicitly-related cluster applications cannot be removed here. It does not describe failure modes (e.g. what happens if no relationship exists) or confirm whether a repeat call errors, which matters given idempotentHint=false.

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?

The destructive effect and scope are front-loaded, and the admin restriction and side-effect note are ordered sensibly. The clause about cluster applications ('those are related with nothing stated') is grammatically tangled and takes a re-read, which is the main reason it falls short of 5.

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 destructive, three-parameter tool with no output schema, the description covers the actor restriction, the reversibility of review effects, and the class of relationships it cannot touch. Only the response/confirmation behaviour and the no-op case are left unstated.

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 the schema already documents all three parameters, including installation_id sourcing via list_credentials and the symmetry of the two repository arguments. The description only echoes the order-insensitivity point, adding no new syntax or constraint beyond the structured fields — the baseline for full coverage.

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 states a specific verb and resource ('Stop AI code reviews relating two repositories: removes the stated relationship') and immediately scopes it to 'one GitHub App installation'. It explicitly distinguishes itself from list_related_repositories, so an agent can choose between the read and the removal without opening a 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?

It gives a precondition ('Organisation admins only') and an explicit exclusion ('cannot unrelate applications installed on the same cluster - those are related with nothing stated'), and points at list_related_repositories to check state first. What is missing is a direct pointer to relate_repositories as the inverse operation, so the when-to-use case is clear but the alternative set is only partly mapped.

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.