Skip to main content
Glama

invoke_model

Read-onlyIdempotent

Run inference against a served model by sending 1–20 text inputs, optionally to a named workspace, to get model predictions.

Instructions

Run inference against a served model.

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": {
      "model": "<model>",
      "inputs": "<inputs>"
    },
    "name": "invoke_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYes
inputsYes1-20 text inputs.
workspaceNoNamed workspace. Omit to use the default workspace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description adds nothing beyond the one-line purpose: no cost/latency expectations, no batching or rate-limit context, and no note that inference calls may consume served-model capacity.

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?

A single front-loaded sentence with zero waste, but the brevity is under-specification rather than economy: there is no second sentence carrying the precondition or return shape.

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

Completeness2/5

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

For a tool whose entire value is the inference output, there is no output schema and no statement of what comes back (scores, labels, logits) or in what order relative to the inputs. Combined with an undocumented 'model' parameter and a 1-20 input constraint handled only by the schema, the definition leaves real gaps.

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 coverage is 67%, and the description adds no parameter meaning at all. In particular the 'model' parameter has no schema description and the description does not explain it must reference a currently served model, which is the most likely source of invocation error.

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+resource: 'Run inference against a served model.' An agent can tell this is a prediction call rather than a job or cluster operation. It stops short of distinguishing itself from sibling vector_search, which could also be read as scoring a model against inputs.

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

Usage Guidelines2/5

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

No when-to-use/when-not guidance and no prerequisites. It never says how to obtain a valid model identifier (e.g., via list_models) or how a model must already be served, which is the key precondition for this tool to succeed.

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