Skip to main content
Glama

Run model scan

run_model_scan
Destructive

Run a released model parameter scan with exact parameters and destination. Validates internally, then queues one job. Requires authorization and compute entitlements. Retain the UUID for retries; inspect request_status after uncertainty.

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": {
      "parameters": "<parameters>",
      "destination_project_id": "<destination_project_id>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "run_model_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputsNo
limitsNoOptional maximum cost and resources; missing estimates block execution. 1000 cpu_millis = 1 vCPU.
parametersYes
agent_run_idNo
idempotency_keyYesOne UUID retained for this logical mutation and its retries.
capability_versionNo
destination_project_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior4/5

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

Beyond the annotations, the description discloses that validation happens internally and execution is asynchronous (queues one job), plus the auth and entitlement prerequisites and the retry/status-check protocol. It does not explain what the destructiveHint=true means in practice — e.g. whether credits are consumed or whether a queued job can be undone — leaving the highest-risk behavior only implied.

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?

Four short sentences, front-loaded with the action and followed by validation/queueing behavior, prerequisites, and retry advice — no filler. The final clause 'inspect request_status after uncertainty' is telegraphic enough to be slightly ambiguous about what 'uncertainty' means.

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 an async mutation with 7 parameters and nested cost controls, the description covers the essentials an agent needs to call it safely and retry correctly, and an output schema exists so return values needn't be described. The main gap is the cost/resource limits parameter and the credit-consumption implications of a destructive, non-idempotent call.

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

Parameters2/5

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

Schema description coverage is only 29% across 7 parameters, so the description needs to compensate, but it only vaguely gestures at 'exact parameters and destination'. It says nothing about the limits object (GPU/CPU/credit/memory caps and the fact that missing estimates block execution), inputs, agent_run_id, or capability_version — the idempotency_key is only indirectly referenced as 'the UUID'.

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 gives a specific verb and resource ('Run a released model parameter scan') plus the scope that it queues a single job with supplied parameters and destination. It is clear what the tool does, but it never distinguishes itself from siblings like run_model_fit or run_model_simulation, so an agent must infer scan-vs-fit-vs-simulation from the name alone.

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

Usage Guidelines3/5

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

It supplies useful operational guidance: requires authorization and compute entitlements, retain the UUID for retries, and check request_status when the outcome is uncertain. However, it gives no criteria for choosing this tool over run_model_fit or run_model_simulation, and no when-not guidance (e.g. prerequisites for a released model or missing cost estimates).

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