Skip to main content
Glama

run_ollama_task

Delegates heavy code, text generation, or analysis sub-tasks to a local or cloud Ollama model, reserving Claude tokens for work needing Claude-level reasoning.

Instructions

Delegates a heavy code, text generation, or analysis sub-task to a local or cloud Ollama 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": {
      "prompt": "<prompt>"
    },
    "name": "run_ollama_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoThe Ollama model tag to invoke. Use list_ollama_models to see what's pulled.qwen-context:h-q4_0-24k
formatNoConstrain output: "json" for any JSON, or a JSON Schema object to force an exact shape.
promptYesThe specific task or prompt to send to the Ollama model.
num_ctxNoContext override; inherits the model setting when omitted.
timeout_msNoRequest deadline in milliseconds; defaults to the server's configured deadline (120 seconds by default).
num_predictNoOutput ceiling override; defaults to the smaller of the saved model ceiling and 8192 tokens.
system_promptNoOptional instructions framing the model's role.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden and falls short: it does not state that this is a blocking inference call, how latency or cost behaves, whether prompt/output is retained, or whether the call has side effects. 'Local or cloud' hints at differing backends but does not explain the implications for an agent.

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?

A single front-loaded sentence with no filler or repetition. It is efficient, though the brevity borders on under-specification for a seven-parameter inference tool.

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?

There is no output schema, so the description should describe what comes back (raw text, JSON per the format parameter, truncation under num_predict), and it says nothing. It also omits practical context such as the default 120-second deadline and the model tag hint that appears only in the schema.

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%, so all seven parameters already carry semantics, including the model tag hint to 'list_ollama_models'. The description adds nothing about parameter effects such as how 'format' constrains output or how timeouts interact with the chosen model.

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 ('delegates') plus the resource ('sub-task') and the target ('local or cloud Ollama model'), and it scopes the task types to code, text generation, and analysis. It does not explicitly distinguish itself from the sibling 'list_ollama_models', but the purpose is unambiguous on its own.

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?

The qualifier 'heavy' implies this is for offloading substantial sub-tasks rather than trivial calls, which gives some when-to-use signal. However, there are no explicit conditions, exclusions, or named alternatives for when a direct call or another sibling is preferable.

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