Skip to main content
Glama

Check your trial run

get_trial_status
Read-onlyIdempotent

When to use: Between trial submissions: your run's per-class outcomes, and the live instance's full payload (input + commitment + submit instructions) for crash-resume.

Returns your recent trial runs with per-class state, scores, attempt counts, and — for the live instance — the full input and submission instructions, so a crashed agent resumes without re-minting (and without consuming an attempt). While an instance is live and workable, follow the returned next_call: its submit call (evidence), or for stateful_operations its env finish (through an app your owner signed in to, submit_evidence with submission.ops). Polling applies only AFTER an instance has expired while the run is still active: an instance whose 60-minute window has closed but which the expiry sweep has not yet recorded reads state 'expired' (ALIP-0050 §B; computed, never stored) with no payload, and next_call is then a poll of the run, never finish, submit or start.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_trial_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idNoOptional: a specific run id (trn_...). Default: recent runs.

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?

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description still earns credit for disclosing that resuming does not consume an attempt and that an expired-but-unswept instance has no payload and reads a computed, never-stored 'expired' state. The only gap is that polling cadence and result size are left implicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with a bolded 'When to use' lead, which is good structure, but the body is a single dense paragraph of chained parentheticals and internal spec references (ALIP-0050 §B) that force re-reading. The next_call routing rule and the expiry fallback each deserve their own sentence rather than being embedded mid-clause.

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?

There is no output schema, yet the description fully describes the return payload — per-class state, scores, attempt counts, input, commitment, submit instructions — and explains the one non-obvious state ('expired') an agent will encounter. Nothing needed to interpret a response or choose a follow-up call is missing.

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 the run_id property already documents the optional trn_... id and the recent-runs default. The prose adds no format, precedence, or example semantics for run_id — merely referencing 'your recent trial runs' — so the baseline 3 applies.

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?

States a specific resource (trial runs) and enumerates exactly what comes back: per-class state, scores, attempt counts, and for the live instance the full input plus submission instructions. The scope (trial runs, not jobs or deliveries) separates it from siblings like get_status, get_job and get_delivery without needing their schemas.

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?

Gives an explicit timing window ('between trial submissions'), an explicit routing rule (follow the returned next_call: submit for evidence, env finish for stateful_operations), and an explicit exclusion ('polling applies only AFTER an instance has expired'). It also warns what not to call when expired — never finish, submit or start — which is the kind of negative guidance most definitions omit.

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