Skip to main content
Glama
Sign In

Arbituro

by com.arbituro
OverviewDiscussionsAdmin

Link a pull request

link_pull_request
Idempotent

Put the pull request you opened for a job on that job, so the job shows the work: its title, its state and its CI. The pull request must be in a GitHub repository bound to the job's project. This changes nothing in GitHub. A clause a named check decides is decided by that check on this pull request, including one that has already finished; every other clause still waits on a person.

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": {
      "project": "<project>",
      "job": "<job>",
      "url": "<url>"
    },
    "name": "link_pull_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYesThe job's key, e.g. FLAIR-12.
urlYesThe pull request's address, e.g. https://github.com/acme/api/pull/41.
projectYesThe project's key, e.g. FLAIR.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations, it discloses that the call mutates job-side state but 'changes nothing in GitHub', which prevents the agent from expecting a remote write despite readOnlyHint=false. It also explains the side effect on job clauses: a check-named clause is resolved immediately by that check (even a finished one), while other clauses still require a person. The clause sentence is dense and slightly cryptic, and nothing is said about what happens if the repo/project binding fails.

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?

Purpose and outcome are front-loaded in the first sentence, followed by constraint, external-effect disclaimer, and clause behavior — every sentence carries distinct information. The clause sentence is long and reads awkwardly, costing a point on structure.

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?

With no output schema, the description supplies the outcome ('the job shows the work: its title, its state and its CI') and the main constraint plus side effects, which is enough to call it correctly. It lacks failure behavior when the PR is not in a bound repository, the one gap an agent would plausibly hit.

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% with per-parameter examples, so the baseline is 3. The description earns above that by adding a real constraint the schema cannot express: the URL's repository must be bound to the supplied project, which ties the 'url' and 'project' parameters together semantically.

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 action on a specific resource ('Put the pull request you opened for a job on that job') and immediately names the observable outcome: the job then shows the PR's title, state and CI. An agent can tell exactly what state changes without opening the 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 clear precondition for use ('the pull request you opened for a job') and a hard constraint ('must be in a GitHub repository bound to the job's project'). It does not name when not to use it or point at an alternative tool, but no sibling performs this action, so the routing burden is small.

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

All Arbituro toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources