Skip to main content
Glama
costajohnt

oss-autopilot

by costajohnt
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

untrack

Destructive

Remove a GitHub pull request from your monitored list to stop tracking its progress and updates.

Instructions

Stop tracking a pull request. Removes the PR from your monitored list.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
prUrlYesFull GitHub PR URL to untrack (e.g. https://github.com/owner/repo/pull/123)

Implementation Reference

  • packages/core/src/commands/track.ts:60-69 (handler)
    The implementation of the runUntrack command. In v2, it acts as a no-op as tracking is no longer persistent.
    export async function runUntrack(options: { prUrl: string }): Promise<UntrackOutput> {
  validateUrl(options.prUrl);
  validateGitHubUrl(options.prUrl, PR_URL_PATTERN, 'PR');

  return {
    removed: false,
    url: options.prUrl,
    message: 'In v2, PRs are fetched fresh on each daily run — there is no local tracking list to remove from.',
  };
}
  • packages/mcp-server/src/tools.ts:144-154 (registration)
    Registration of the untrack tool in the MCP server.
    // 6. untrack — Stop tracking a PR
server.registerTool(
  'untrack',
  {
    description: 'Stop tracking a pull request. Removes the PR from your monitored list.',
    inputSchema: {
      prUrl: z.string().describe('Full GitHub PR URL to untrack (e.g. https://github.com/owner/repo/pull/123)'),
    },
    annotations: { readOnlyHint: false, destructiveHint: true },
  },
  wrapTool(runUntrack),

Tool Definition Quality

A4/5.0
Behavior4/5

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

Annotations indicate destructiveHint=true; description adds critical scope clarification that removal is 'from your monitored list' only, preventing misinterpretation that the actual PR might be deleted. No contradictions with readOnlyHint=false.

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?

Two efficient sentences with zero waste. First sentence states the action, second clarifies the scope of destruction. Front-loaded with the imperative action and appropriately sized for the tool's complexity.

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?

Complete for a single-parameter destructive operation. Annotations cover safety profile, schema covers input requirements, and description clarifies the behavioral scope. No output schema exists, but description sufficiently explains the mutation effect.

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% (prUrl fully documented), establishing baseline 3. Description does not add parameter syntax details beyond schema, but references 'PR' which aligns with the parameter purpose.

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?

Specific verb ('Stop tracking') plus resource ('pull request') clearly identifies the operation. Implicitly distinguishes from sibling 'track' tool by stating the inverse action, making the relationship clear without naming it explicitly.

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?

Implies usage context through 'Stop tracking' (suggests use when monitoring is no longer needed), but lacks explicit when-to-use guidance, prerequisites, or named alternatives like the 'track' sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/costajohnt/oss-autopilot'

If you have feedback or need assistance with the MCP directory API, please join our Discord server