Skip to main content
Glama

run_status

Check a run's stage, panel verdicts, scoreboard, output files, and cost. Optionally wait for another call to finish, get only new progress, or request a short resume brief.

Instructions

State of one run: stage reached, panel verdicts, scoreboard, files produced, cost. Pass brief=true for a short, regenerated-on-demand resume brief instead - what a returning session with fresh context needs to re-enter the run. Pass wait_seconds (1-90; use 90) to hold the call until another call finishes, the run stops running, or the time is up, and progress in the result lists what finished meanwhile. until='settled' holds across finished calls and returns only when the run stops running or the time is up. Pass since (the progress.cursor from the last call, or 0 for everything so far) to get only what is new.

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": {
      "run": "<run>"
    },
    "name": "run_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
runYes
briefNo
sinceNo
untilNo
wait_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.4
    • changedInput schema / properties / wait_seconds / maximum
      Previous value: -30New value: +90
  2. First observedv0.8.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses long-polling semantics, that the call returns early when another call finishes or the run stops running, that progress lists what finished meanwhile, and the 1-90s wait bound with 'use 90' as the recommended value. It omits failure behavior (unknown run id), whether the call is read-only, and the cost of repeated polling.

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?

Front-loaded with the primary purpose, then one compact sentence per mode, each introducing the parameter it governs. No filler, no repetition of schema constraints beyond the useful 'use 90' recommendation; the density is justified by five under-documented parameters.

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?

Given no annotations, no output schema, and 0% schema coverage, the description supplies the return fields, the waiting/pagination model, and per-parameter semantics, which is nearly enough to call it correctly. Only the `run` identifier and error/timeout edge cases are unaddressed.

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 0%, so the description must compensate, and it explains four of five parameters in real depth: brief's alternate output, wait_seconds' range and recommended value, until's two enum meanings, and since's cursor-or-zero convention. The required `run` parameter is never described (id format, where to obtain it), which is the one remaining gap.

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 concrete verb+resource, 'State of one run', and enumerates the returned content (stage reached, panel verdicts, scoreboard, files produced, cost), so an agent knows exactly what it retrieves. It does not explicitly separate itself from the sibling tree_status or list_runs, leaving some ambiguity about which status tool applies.

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 clear conditional guidance for each mode: use brief=true when re-entering with fresh context, use wait_seconds=90 to block for a finishing call, use until='settled' to wait across finished calls, and pass since with the last progress.cursor for only new events. It never states when to prefer a different status/lookup tool, so routing between siblings is left to inference.

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