Skip to main content
Glama
Sign In

AgentCompute

by io.github.Ockram4444
OverviewDiscussionsAdmin

Read a GPU job result

get_compute_job
Read-onlyIdempotent

Read a previously submitted job by job_id. Returns status, transcript, runtime and reference quality when complete. For queued or running jobs, wait poll_after_seconds before checking again. Failed or expired jobs are not successful results.

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": {
      "job_id": "<job_id>"
    },
    "name": "get_compute_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYesExact job_id returned by submit_compute_job.
access_tokenNoAccount credential from My account; optional with Bearer authentication.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / access_token / description
      Previous value: -"Temporary trial token, unless Bearer authentication is configured."New value: +"Account credential from My account; optional with Bearer authentication."
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Beyond the read-only, idempotent, non-destructive annotations, it discloses asynchronous polling behavior, completion-dependent result availability, and the significance of failed or expired states. It does not clarify whether unsuccessful states are returned normally or surfaced as errors, but the added lifecycle context is substantive.

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?

Four short sentences efficiently cover retrieval, outputs, polling, and unsuccessful outcomes. The primary action is front-loaded, and there is no filler or repeated structured-field content.

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?

For a simple asynchronous read with no output schema, the description supplies the key result fields and enough polling and failure context to support correct invocation. It could be more complete by identifying poll_after_seconds explicitly as a returned value and clarifying the boundary with get_compute_status, but these are modest gaps.

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 description coverage is 100%, and both job_id and access_token are already documented there. The description's reference to a previously submitted job adds little beyond the schema's statement that job_id comes from submit_compute_job, and it adds no further credential guidance.

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 clearly states that the tool reads a previously submitted job by job_id and identifies the principal result fields. Together with the GPU-oriented title and compute-specific name, this gives a clear purpose, but the description itself does not distinguish the tool from get_compute_status or get_studio_job.

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 useful lifecycle guidance: read a submitted job, expect full result details when complete, and wait poll_after_seconds before polling queued or running jobs again. It does not explicitly route status-only checks or other job types to sibling tools, so the guidance is contextual rather than exhaustive.

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

All AgentCompute 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