Skip to main content
Glama

switch_project

Idempotent

Point runtime tools like screenshots, input, UI, and logs at another Godot project's live session when multiple sessions exist. Select an exited game's session to read its logs or stop it.

Instructions

Point the runtime tools (screenshots, input, UI, run_script, debug output, profiling, stop_project) at another project's session. Needed only when several sessions exist; run_project makes its own session current. A session whose game exited can be selected to read its logs or stop it: live is then false and warnings leads. Returns: projectPath, previousProjectPath, live, sessionMode, bridgePort, bridgeResponsive, message. Errors if the project has no session, listing the live ones.

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": {
      "projectPath": "<projectPath>"
    },
    "name": "switch_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectPathYesPath to the Godot project directory whose session becomes the current one. check_project lists the live sessions.

Output Schema

NameRequiredDescriptionDefault
liveYes
messageYes
exitCodeNo
warningsNo
bridgePortYes
projectPathYes
sessionModeYes
bridgeResponsiveYes
previousProjectPathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv4.0.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, idempotentHint=true, destructiveHint=false; the description goes well beyond that by stating the global side effect on sibling tools, the state transition for exited sessions (live becomes false, warnings leads), and the error case ('Errors if the project has no session, listing the live ones'). That error/failure behavior is exactly the kind of context annotations cannot convey.

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 the primary action and effect before the conditional guidance, and every sentence carries operational information. The trailing enumeration of return fields is slightly redundant given an output schema exists, which is the only wasted clause.

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

Completeness5/5

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

For a single-parameter session-switch tool with annotations and an output schema, this covers action, effect scope, usage conditions, session-state caveats, and failure mode. Return values are backed by the output schema, so the brief mention is sufficient rather than a gap.

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 already documents itself, including a pointer to check_project, so the baseline would be 3. The description adds meaning beyond that by explaining that a session may be selected even after its game exited, clarifying what kinds of paths are valid inputs.

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 and target: 'Point the runtime tools (screenshots, input, UI, run_script, debug output, profiling, stop_project) at another project's session.' It enumerates exactly what is affected and implicitly distinguishes itself from run_project, which 'makes its own session current.'

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

Usage Guidelines5/5

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

Explicitly states the selection condition ('Needed only when several sessions exist') and names the alternative that removes the need (run_project). It also gives a second valid use case — selecting an exited session to read logs or stop it — so both when-to-use and the sibling relationship are covered.

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