Skip to main content
Glama

Watch pipeline run

watch_pipeline_run
Read-only

Wait for an Ankra Pipelines run of a connected repository to conclude. Blocks up to 45 seconds and returns the settled run (outcome, each step's outcome, the first failing step) or timed_out true with the last observed state. Nothing notifies this client when a run ends later: on timed_out, call watch_pipeline_run again with the run_id it returned to keep waiting. Identify the run by head_sha (the commit) or run_id (the run's UUID, or its run number in the repository: 3630 for run #3630); branch disambiguates head_sha lookups. provider defaults to github; timeout_minutes is ignored here. Read a failing step's log with get_pipeline_step_logs. The repository must already be connected to Ankra Pipelines.

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": {
      "owner": "<owner>",
      "repo": "<repo>"
    },
    "name": "watch_pipeline_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
repoYesRepository name.
ownerYesRepository owner (organisation or user).
branchNoBranch name to disambiguate head_sha lookups.
run_idNoPipeline run to watch, alternative to head_sha: its UUID, or its run number in this repository (3630 for run #3630).
head_shaNoCommit SHA whose pipeline run to watch. One of head_sha/run_id/pull_request_number is required.
providerNoSource control provider: github, gitlab, or bitbucket_cloud. Defaults to github.
timeout_minutesNoMinutes to keep watching before the platform reports a timeout instead (default 30, max 60; for pull_request_number, default 1440, min 30, max 4320).
pull_request_numberNoAn open GitHub pull request to wait on until it merges or is closed, instead of head_sha/run_id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / head_sha / description
      Previous value: -"Commit SHA whose pipeline run to watch. One of head_sha/run_id is required."New value: +"Commit SHA whose pipeline run to watch. One of head_sha/run_id/pull_request_number is required."
    • addedInput schema / properties / pull_request_number
      Added value: +{
      +  "description": "An open GitHub pull request to wait on until it merges or is closed, instead of head_sha/run_id.",
      +  "type": "integer"
      +}
    • changedInput schema / properties / timeout_minutes / description
      Previous value: -"Minutes to keep watching before the platform reports a timeout instead (default 30, max 60)."New value: +"Minutes to keep watching before the platform reports a timeout instead (default 30, max 60; for pull_request_number, default 1440, min 30, max 4320)."
  2. Changed1 schema field changed
    • changedInput schema / properties / run_id / description
      Previous value: -"Explicit pipeline run id to watch; alternative to head_sha."New value: +"Pipeline run to watch, alternative to head_sha: its UUID, or its run number in this repository (3630 for run #3630)."
  3. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true; the description goes well beyond by disclosing the 45-second blocking window, that the call settles into either a completed run or timed_out with last observed state, and critically that nothing notifies the client later so the caller must re-invoke. For a long-polling tool that is the exact behavioral context an agent needs.

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 core action and its blocking limit are front-loaded, and each subsequent sentence carries distinct operational information. It is dense for one paragraph, and a couple of clauses (the run-number example, the provider default) duplicate the schema, so it is not maximally tight.

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?

With 8 parameters and no output schema, the description supplies the missing return shape itself (outcome, each step's outcome, first failing step, or timed_out with last state) along with the polling contract and the repository-connection prerequisite. An agent can invoke and continue correctly without opening anything else.

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%, and most of the description's parameter prose (run_id accepts a UUID or run number, branch disambiguates head_sha, provider defaults to github) restates the schema verbatim. The one genuinely additive detail is 'timeout_minutes is ignored here', which resolves a conflict an agent would otherwise misread; that earns a bit above baseline but not much.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'Wait for an Ankra Pipelines run of a connected repository to conclude.' Naming Ankra Pipelines separates it from GitHub-Actions-style siblings like watch_workflow_run, though it never explicitly contrasts with that obvious confusion candidate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states exactly when to call it, what to do on the timed_out path ('call watch_pipeline_run again with the run_id it returned'), which sibling to use next for diagnosis ('Read a failing step's log with get_pipeline_step_logs'), and a hard prerequisite ('The repository must already be connected'). That is explicit when, when-not-and-what-instead, and prerequisites in one place.

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.