get_project_statistics

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description need not repeat safety. It adds the context of a 'static scan' and enumerates the exact data collected, which helps the agent predict behavior without contradicting annotations.

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 sentence that front-loads 'Project overview' and lists the metrics compactly. No fluff or irrelevant details.

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?

For a zero-parameter tool without an output schema, the description conveys the breadth of return data. It could be slightly more explicit about the output format (e.g., a structured object), but the listed items make the return value largely predictable.

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 tool has zero parameters, so the baseline is 4. The description adds no parameter-specific semantics, but none are needed since the schema already covers everything (empty properties).

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 provides a project overview with specific metrics (file/script/scene/resource counts, GDScript lines, autoloads, main scene, input-action count, Godot version). It distinguishes itself from sibling tools like get_godot_version by offering a broader scope.

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 phrase 'Project overview' implies a clear use case for a high-level summary, and 'Read-only static scan' indicates safe, non-interactive usage. However, it does not explicitly name alternatives or exclusion criteria, so it falls short of full guidance.

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