start_debug_session

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

Annotations only say readOnly=false, openWorld=true, destructive=false; the description adds the genuinely important side effect that an existing game run is terminated, plus the scope constraint that no addons or project settings are touched. It stops short of describing session lifetime, whether the session must be closed with close_session, or how the handle is obtained.

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?

Three short sentences, purpose first and side effects after, with no filler or repetition of the title. Each sentence carries distinct information (what it does, what it does not do, what it overwrites).

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?

With no output schema and a mutating, open-world tool, the description leaves open how the session handle is returned and how follow-up tools (get_debug_output, stop_project, close_session) attach to it. For a session-starting tool in a dense sibling set, that is a meaningful gap, though the core contract is conveyed.

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 description coverage is only 40%, so the description needs to compensate and it does not: headless, scenePath, and projectPath are undocumented in both places, and only sessionId and annotations carry schema text. The description contributes zero parameter-level meaning beyond the bare purpose statement.

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 gives a specific verb+resource ("Run a temporary live debug session") and distinguishes it from configuration-style siblings via the exclusion of addon install and project-setting changes. It does not explicitly name the nearest alternatives (run_project, run_scene_test, launch_editor), so the differentiation is implied rather than stated.

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?

"Does not install addons or change project settings" is useful negative guidance that steers the agent away from settings/addon tools, and "Replaces the current game run" hints at when it is appropriate. But no sibling is named as the alternative, and there is no statement of prerequisites or when to prefer run_project or run_scene_test instead.

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