Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Long job as a task (tasks)

run_task
Read-only

Tests MCP client task support by simulating a long-running job with polling, progress updates, configurable outcomes, and halfway yes/no confirmation prompts.

Instructions

Run a fake long job. Clients with task support get a task handle at once and poll it (tasks/get); others wait for the result. Options: seconds, steps, outcome (success, tool_error, failure) and askConfirmation (pauses halfway for a yes/no: task status input_required).

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": "run_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsNoNumber of steps; each one updates statusMessage
outcomeNosuccess = normal result; tool_error = result with isError (task still "completed"); failure = JSON-RPC error (task "failed")success
secondsNoHow long the fake job runs
askConfirmationNoHalfway through, ask the user to continue (task status input_required)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true and idempotentHint=false; the description adds the genuinely useful behavior: an immediate task handle with tasks/get polling, blocking fallback, the input_required pause for askConfirmation, and how each outcome maps to task status. That is substantial context beyond the annotations, though return payload details are absent.

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, front-loaded with purpose followed by the async behavior and the option summary; no filler. The heavy parenthetical compression makes it slightly dense to parse but every clause carries information.

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

Completeness4/5

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

For a four-optional-parameter, no-output-schema tool, the description covers the async execution model, polling path, confirmation pause, and outcome-to-status mapping. An agent can call it correctly without additional context, with only minor gaps around return payload shape.

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 every parameter is already documented in the schema, including enum meanings for outcome. The description only summarizes the option list and the input_required consequence of askConfirmation, adding little beyond the structured fields.

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 states a specific verb and resource ("Run a fake long job") and immediately explains the defining trait: task handle plus polling for task-capable clients versus blocking wait for others. It does not name or distinguish run_task_required or slow_task, so it stops short of full sibling differentiation.

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?

Usage is implied rather than stated: the client-capability branching tells an agent what will happen, which suggests this is for exercising task support. There is no explicit when-to-use/when-not guidance relative to the similarly named run_task_required or slow_task siblings.

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