Skip to main content
Glama

executor_probe

Measures local model capabilities—native tool calls, schema-forced JSON, reasoning, and speed—and stores results so Tandem MCP adapts delegation; force reruns the check.

Instructions

Measure what a local model can do on this server: native tool calls, JSON schema forced by the server, reasoning text, speed. The result is stored and the tools adapt to it: a model without tool calling still does delegate through JSON replies. Runs by itself at the first use of a model; force repeats it (after a change of server settings or of chat template).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "executor_probe"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNo
modelNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.1

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description carries the burden and does well: it discloses that results are persisted, that downstream tools change behavior based on the result, and that the probe triggers automatically on first model use. It omits the practical cost profile — how long the probe runs or that it consumes model inference — which matters for a tool that exercises an LLM.

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 dense sentences that front-load what is measured, then persistence/adaptation, then automatic invocation. Nothing is filler. The middle sentence's 'a model without tool calling still does delegate through JSON replies' is slightly indirect but earns its place by explaining why the stored result matters.

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 need not be described, and the auto-run behavior is well covered. However, with zero schema description coverage, the unexplained 'model' parameter and the absence of any duration or cost expectation leave gaps for a tool that performs inference.

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%, so the description must explain both parameters. It explains 'force' meaningfully (repeat after server-settings or chat-template changes) but says nothing about 'model' — whether an empty value means the active model or a first-discovered one. Half the parameters are covered, so a middling score rather than a low one.

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?

Names a specific action and object: it probes a local model for native tool calling, forced JSON schema, reasoning text, and speed on this server. That is far more specific than a tautology, though it never explicitly contrasts itself with the sibling executor_status or delegate, so the agent must infer the division of labor.

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

Usage Guidelines4/5

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

Gives real routing guidance: it 'runs by itself at the first use of a model', and 'force repeats it (after a change of server settings or of chat template)'. That tells the agent when a manual call is warranted versus when the system handles it. It falls short of a 5 because it never states the negative case plainly, e.g. 'do not call unless settings changed'.

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