Skip to main content
Glama

read_output

Reads and consumes newly buffered output for a Minecraft task, returns its execution state, and waits until output arrives, the task ends, or wait_ms elapses. Use one reader per task.

Instructions

Read and consume newly buffered output for a task, plus its native execution state. Use one reader per task. Overflow is marked inline as [ …N bytes truncated… ]. Errors include script stack traces and precede output. Waits until output arrives, the task ends or wait_ms elapses.

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": {
      "task": "<task>"
    },
    "name": "read_output"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYes
wait_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.0
    • changedInput schema / properties / wait_ms / maximum
      Previous value: -10000New value: +30000
  2. First observedv0.2.1

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses that reading is consuming/draining, that truncation appears inline as a marked token, that errors carry stack traces and precede output, and that the call blocks until output, task end, or wait_ms. It stops short of saying whether consumed output is lost permanently or what permissions are required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, purpose front-loaded, each one carrying distinct information: identity, reader constraint, truncation marker, error ordering, and blocking semantics. Nothing is redundant and nothing needs re-reading.

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 two-parameter tool with no output schema and no annotations, the description covers the important return-shape facts (output text, execution state, inline truncation, error ordering) and the blocking contract. It leaves the structure of the 'execution state' payload and the task identifier format undefined.

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 compensate for both parameters. It does explain wait_ms indirectly by describing the blocking behavior and its timeout condition, but it never clarifies what the `task` value should be (ID vs. name) or its format.

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 verb pair (read/consume) and a specific resource (newly buffered output for a task), and adds that native execution state is returned too. That is enough for an agent to tell this apart from execute/stop/screenshot/chat without opening the schema, though it never explicitly contrasts with those siblings.

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?

"Use one reader per task" is a real usage constraint that warns against multiple concurrent consumers, and the blocking clause implies this is called after a task is launched. However, there is no explicit when-to-use versus when-not-to-use guidance and no pointer to an alternative for draining or inspecting output.

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

Deploy Server

Other Tools