Skip to main content
Glama

Run capability

run_capability
Destructive

Run a released scientific capability with exact inputs 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": {
      "capability_id": "<capability_id>",
      "destination_project_id": "<destination_project_id>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "run_capability"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputsNo
limitsNoOptional maximum cost and resources; missing estimates block execution. 1000 cpu_millis = 1 vCPU.
parametersNoCapability-specific values under the field name parameters (not params). Call get_capability first and validate against its parameters_schema.
agent_run_idNo
capability_idYes
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

A3.6/5.0
Behavior4/5

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

Annotations already declare non-read-only, destructive, non-idempotent, closed-world; the description adds real value on top by explaining the internal validate-then-queue-one-job flow, the authorization/entitlement gate, and the retry discipline of retaining the UUID and checking request_status. It does not say what a failed validation returns or how long queued jobs persist, but the mutating behavior is well disclosed.

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?

Three tight sentences with the action and its effect front-loaded, followed by prerequisites and then retry guidance in the order an agent needs them. Only minor slack in the vague phrase 'with exact inputs and destination,' which could have named the parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is complex (8 params, nested objects, mutations), but annotations and the output schema carry the safety profile and return shape, so the description needn't explain those. The gap is that five parameters, including resource/cost limits that 'block execution' per the schema, go unmentioned in the description, leaving the agent reliant on partial schema text.

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 only 38% across 8 parameters, and the description covers just the idempotency UUID ('retain the UUID for retries') while saying nothing about limits, capability_version, agent_run_id, or the inputs array shape. The 'exact inputs and destination' phrasing gestures at inputs/destination_project_id but adds no format or constraint detail beyond the schema.

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?

States a specific verb and resource ('Run a released scientific capability') plus the two things that define the call: exact inputs and a destination project. It doesn't distinguish itself from siblings like run_model_fit or run_model_scan, but the generic-vs-specialized relationship is reasonably inferable from the name and the 'released capability' framing.

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?

Provides prerequisites ('requires authorization and compute entitlements') and routes post-call uncertainty to request_status, which is genuinely useful guidance. However, it never states when to choose this tool over the sibling run_* tools or get_capability (the schema says to call get_capability first, but the description does not), leaving selection largely implied.

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