godot_audit_assets

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

Annotations already provide readOnlyHint=true and destructiveHint=false. The description adds the narrow audit context (unused assets, missing dependencies, broken paths) which goes beyond what annotations declare, but it does not explain things like performance impact, report location, or types of results. This is adequate but not rich behavioral disclosure.

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 one short sentence that begins with a verb and has no unnecessary wording. It is efficient and prohibits wasted space, though it is not as 'opinionated' or as directive as it could be. It avoids vagueness and is concise.

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?

The core scan intent is spelled out, and the output schema is present, so return-value documentation is not needed. However, there is no mention of how ignorable parameters widen or narrow the scan, and no guidance on when to pick this over adjacent sibling tools. It is enough for basic recognition but not strongly complete for nuanced selection.

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?

The schema description coverage is 0%, and the description does not mention ignore_paths or include_extensions at all. Since the effective coverage is near zero, the description must compensate by summarizing parameter behavior, but it does not. An agent gets no non-schema help in deciding how to configure the audit parameters.

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 uses a strong, specific verb ('Scan') with a clear resource ('the project') and three concrete audit dimensions ('unused assets, missing dependencies, or broken paths'). This clearly distinguishes the tool from similar siblings such as godot_audit_orphan_nodes or godot_clean_orphans.

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?

The intended use can be inferred from the imperative 'Scan project', but there is no explicit when-to-use guidance or alternatives list. No exclusions are given, and sibling tools like godot_get_dependencies or godot_clean_orphans are not referenced. This puts it at an implied-usage level rather than providing concrete decision guidance.

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