Skip to main content
Glama

Turn off automatic updates

githubSyncDisable
Idempotent

Turn automatic updates OFF for one owned project — the Automatic updates switch in the Source card on its Versions page: Tofu stops deploying on a push to the recorded branch, and a build already running is left to finish. It takes no confirmation, deliberately: turning updates off starts no deployment and changes nothing about the app, where turning them on starts deployments that count against the account’s allowance. The import is kept — the source still records the repository, branch, commit and app root — so this is not a way to take the code away from GitHub; it cannot delete a project or deployment, or change which repository Tofu follows. It stays usable when the GitHub connection, the App or the account’s plan has lapsed. Idempotent: disabling an already-disabled project changes nothing, and the answer says where the project now stands (the same read githubStatus gives).

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": {
      "projectId": "<projectId>"
    },
    "name": "githubSyncDisable"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYes

Output Schema

NameRequiredDescriptionDefault
paidYes
stateYes
branchYes
reasonYes
sourceYes
pendingYes
lastCommitShaYes
rootDirectoryYes
lastDeliveryAtYes
lastDeploymentIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations: a running build is left to finish, the import/repository/branch/commit/app root are retained, it cannot delete a project or deployment or change the tracked repository, and it remains usable when the GitHub connection, App, or plan has lapsed. These are exactly the side-effect and survival details an agent needs for a mutation tool.

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?

Front-loaded with the core action and UI anchor, then layered with constraints; almost every clause carries distinct information. It is dense and long for a single-parameter tool, and the idempotency restatement overlaps the idempotentHint annotation, but no sentence is filler.

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?

For a mutation tool with an output schema, this covers side effects, non-destructive scope, permission/lapse conditions, and return-shape hinting. Combined with the annotations, an agent has everything needed to call it correctly.

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?

There is one parameter (projectId) with 0% schema description coverage, so the description carries the burden, and it only conveys that the project must be 'owned' and singular. The UUID format and identifier expectations are left entirely to the schema pattern, so meaning added is minimal.

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 precise verb and resource — turn automatic updates OFF for one owned project — and anchors it to the visible UI element (the Automatic updates switch on the Versions page), which lets an agent map the call to a concrete action. It also distinguishes itself from the read path by noting the response is 'the same read githubStatus gives.'

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 clearly scopes usage to an 'owned project' and explains why no confirmation is requested (disabling starts no deployment, unlike enabling), which tells an agent when this is safe to call freely. It does not spell out an explicit when-not or name a sibling 'enable' alternative, so it falls short of full routing 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.

Resources