Skip to main content
Glama

ask

Delegate drafting, translation, boilerplate, or classification to the local executor; optional JSON schemas and multi-sample agreement checks flag uncertain results.

Instructions

A text task for the local executor (drafting, translation, boilerplate, classification).

json_schema: optional JSON schema (as a string) that the answer must follow. samples: 2 to 5 runs the task several times and reports how many runs agree. Agreement below 1.0 on a factual or structured task means the executor is unsure: check or do it yourself.

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": "ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo
promptYes
samplesNo
max_tokensNo
json_schemaNo
system_promptNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.1

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the whole load. It does disclose non-obvious behavior for two parameters — samples triggers multiple runs with an agreement report, and json_schema constrains the answer shape — but says nothing about the model parameter (empty default), max_tokens, system_prompt, or whether this is a slow, offline, or rate-limited call.

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?

Tight and front-loaded: the purpose comes first, followed by the two parameter behaviors that matter most for interpretation. A line defining model or max_tokens would have been a better use of space than nothing, but there's no filler or repetition.

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?

An output schema exists, so return values needn't be explained. For a six-parameter tool with zero annotation coverage, the description still leaves four parameters undefined and doesn't say what the local executor is — an agent has to guess whether this is fast, offline, or model-selectable.

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 0% across six parameters, so the description must compensate and it only partially does, explaining json_schema (passed as a string, answer must conform) and samples (count and agreement interpretation). Model, max_tokens, system_prompt, and prompt itself remain entirely undefined anywhere, so half the surface is undocumented.

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 names a specific capability — running a text task (drafting, translation, boilerplate, classification) on the local executor — and the examples make the intended work type concrete. It never names a sibling such as ask_local_qwen, delegate, or generate_code_with_qwen, so an agent can't tell from the text alone why it would pick this over those.

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?

There is real guidance on one dimension: use 2-5 samples for repeated runs and distrust agreement below 1.0 on factual or structured tasks. There is no guidance on when to use this versus the local-model or delegation siblings, and no statement of prerequisites or typical latency/cost.

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