Skip to main content
Glama

NoGPU

nogpu_report

Free report: send an LLM's past decisions, 160-10,000 rows with at least 2 labels, either as rows ([{"text": ..., "label": ...}]) or as jsonl (the same rows as JSONL text; a JSON array or a CSV with a header row also works), at most 20 MB. NoGPU trains a small CPU model on them and measures what share of the decisions it answers alone, how often those answers match the LLM (with a 95% lower bound) on held-out rows, and its latency. Waits up to 40 seconds; if the report is not ready by then, call nogpu_status with the returned job_id and claim_token. claim_token and report_url (the token is after its #) open the job: treat both as secrets. Free reports through this endpoint come from one shared daily pool. Data is deleted within 24h. source says where the rows came from: agent (default), the app's stored history, rows logged by a collect snippet, or a given file.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
rowsNo
jsonlNo
sourceNoagent

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the synchronous-wait ceiling (40s), the async fallback, that claim_token and report_url must be treated as secrets, that data is deleted within 24h, that the free tier is a shared quota pool, and precisely what the report measures including a 95% lower bound. These are exactly the operational facts an agent needs and none are recoverable from readOnlyHint/destructiveHint/openWorldHint alone.

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 constraints are front-loaded and almost every clause carries distinct information, but the single dense paragraph with stacked parentheticals (format alternatives, secret handling, source enumeration) makes it harder to scan than it needs to be. Some tightening of the nested asides would improve it without losing content.

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?

For a job-creating tool with three loosely-typed optional parameters and no output schema, the description covers input formats, size and row bounds, the wait/timeout contract, secret handling, retention, quota implications, and what the returned report contains. Nothing an agent needs in order to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does so: it specifies the `rows` object shape ([{"text": ..., "label": ...}]), that `jsonl` accepts JSONL text but also a JSON array or CSV with a header row, the 20 MB ceiling, and enumerates all four `source` values with concrete meanings. That is substantially more than the bare enum and type declarations in the schema.

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 names a specific verb and resource — send rows of LLM decisions, get back a trained CPU model's agreement/coverage/latency report — and is clearly distinct from the sibling tools (nogpu_status polls, nogpu_buy is the paid path, nogpu_delete cleans up). An agent can tell exactly what this tool produces 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 an explicit input contract (160–10,000 rows, at least 2 labels, max 20 MB) and a concrete escalation path: if not ready in 40 seconds, call nogpu_status with the returned job_id and claim_token. The note that free reports draw from one shared daily pool implies nogpu_buy is the paid alternative, but the buy path is never named outright, so the alternative-selection guidance is clear rather than complete.

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.