attach_project

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

No annotations provided, so description carries full burden. It discloses injection of McpBridge autoload, marking project active, and waitForBridge polling up to 15s. Mentions limitation of get_debug_output. However, doesn't explain side effects like repeated calls or permanence of autoload injection.

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

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

The description is a single paragraph of four sentences, front-loaded with purpose and structured logically: purpose, when-to-use, usage steps, and limitation. No wasted words.

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

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

No output schema exists, but description covers key effects (injecting autoload, marking active, polling). It addresses a sibling tool limitation (get_debug_output). However, return values or success confirmation are not explicitly stated, leaving minor gaps.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the two-step usage pattern and clarifying the waitForBridge parameter's polling behavior (up to 15s). This contextualizes the parameters beyond mere schema descriptions.

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

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

The description clearly states the tool's purpose: 'Attach runtime MCP tools to a manually launched Godot process without spawning one.' It distinguishes from sibling 'run_project' by specifying the non-standard use case.

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

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

Explicitly states when to use ('only when the user is running Godot themselves') and not ('for the standard case, use run_project'). Provides step-by-step guidance: call once before launch, then with waitForBridge:true. Lists alternatives (detach_project, stop_project) and notes unavailability of get_debug_output.

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