register_autoload

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

Annotations declare a non-read-only, non-destructive, open-world mutation; the description adds real context beyond that — the validation performed (path and built-in name conflicts), the explicit scope limit (no script/runtime compatibility checking), and the refusal-unless-replace guardrail. It stops short of saying which project file is written or what happens to dependent scenes at runtime.

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 dense sentences with zero filler: capability first, then validation scope, then the override/dry-run controls. Every clause adds information an agent needs before calling.

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 an output schema present the description needn't explain returns, and annotations already cover the safety profile, so the remaining burden is behavior and parameters — both addressed. For a 7-parameter mutation tool this is complete enough to invoke correctly.

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 0%, so the description must carry parameter meaning, and it does for most: name (conflict against built-in names), resourcePath (must be an existing .gd/.cs/.tscn/.scn), singleton (named singleton vs plain autoload), replace, dryRun, expectedHash. Only projectPath and the exact hash semantics of expectedHash are left to inference.

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?

States a specific verb and resource ("Register a named singleton or plain autoload") plus the exact accepted resource types (.gd/.cs/.tscn/.scn). This cleanly distinguishes it from the sibling unregister_autoload and from create_resource, which handles resources but not autoload registration.

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?

Gives clear preconditions and override paths: conflicts are checked, a different existing entry is refused unless replace:true, and dryRun/expectedHash are offered for safe application. It does not explicitly say when to prefer unregister_autoload + re-register over replace:true, so the alternative-selection guidance is implicit rather than spelled out.

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