Skip to main content
Glama

get_debug_output

Read-only

Read captured stdout/stderr from a running or crashed Godot project to diagnose script errors, missing nodes and crash backtraces. Logs persist after exit until the project is stopped.

Instructions

Read captured stdout/stderr from a spawned Godot project. Use whenever a runtime tool fails unexpectedly: script errors, missing nodes and crash backtraces surface here. Still works after the process exits or crashes; the logs are kept until stop_project. Returns: projectPath, sessionMode, output and errors (last limit lines each, default 200), running (false after exit) and exitCode after exit. An attached session captures nothing: output, errors and running are null and warnings leads.

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": "get_debug_output"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax lines to return, a whole number of 1 or more (default: 200, from end of output)

Output Schema

NameRequiredDescriptionDefault
tipNo
errorsYesNull in an attached session, which captures nothing.
outputYesNull in an attached session, which captures nothing.
runningYes
exitCodeNo
warningsNo
projectPathYes
sessionModeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changedv4.0.1
    • changedInput schema / properties / limit / description
      Previous value: -"Max lines to return (default: 200, from end of output)"New value: +"Max lines to return, a whole number of 1 or more (default: 200, from end of output)"
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • changedInput schema / properties / limit / type
      Previous value: -"number"New value: +"integer"
    • removedOutput schema / properties / attached
      Removed value: -{
      -  "type": "boolean"
      -}
    • addedOutput schema / properties / errors / description
      Added value: +"Null in an attached session, which captures nothing."
    • changedOutput schema / properties / errors / type
      Previous value: -"array"New value: +[
      +  "array",
      +  "null"
      +]
    • addedOutput schema / properties / output / description
      Added value: +"Null in an attached session, which captures nothing."
    • changedOutput schema / properties / output / type
      Previous value: -"array"New value: +[
      +  "array",
      +  "null"
      +]
    • addedOutput schema / properties / projectPath
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / sessionMode
      Added value: +{
      +  "enum": [
      +    "spawned",
      +    "attached"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / warnings
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / required
      Added value: +[
      +  "projectPath",
      +  "sessionMode",
      +  "output",
      +  "errors",
      +  "running"
      +]
  2. Addedv3.1.1
  3. Removedv3.0.0
  4. Addedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

readOnlyHint already marks this as a safe read, and the description still adds real operational context: output survives process exit and crashes, retention ends at stop_project, and running/exitCode behave differently post-exit. The final sentence about attached sessions is garbled ('and warnings leads'), which blunts an otherwise valuable caveat.

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?

Front-loaded with purpose and trigger, then a compact return-field summary — dense but mostly earning its space. The truncated trailing clause ('and warnings leads') is wasted, confusing text that should have been a clean sentence about attached sessions.

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 diagnostic read tool with an output schema, the description covers the essentials: what is captured, when to reach for it, retention, post-exit behavior, and the attached-session null case. The only real gap is the garbled attached-session sentence, which leaves the agent guessing at what 'warnings' does.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter is already documented, but the description adds meaning the schema lacks: limit is applied to output and errors separately ('last `limit` lines each'). That is genuine added value above the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource pair: 'Read captured stdout/stderr from a spawned Godot project.' That scope (spawned runtime process, not editor state) cleanly separates it from siblings like get_scene_tree or check_project, so an agent can pick it without opening the schema.

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 an explicit trigger: 'Use whenever a runtime tool fails unexpectedly: script errors, missing nodes and crash backtraces surface here.' It also bounds the window of usefulness ('logs are kept until stop_project') and flags the case where the tool is useless (attached sessions). No sibling alternative is named, so it falls short of a full when/when-not/alternative statement.

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