godot_cast_shape_3d

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

The annotations already disclose that this is a read-only, non-destructive operation, so the description only needs to clarify the physical behavior; the phrase 'physics sweep test' gives some. However, it does not add the qualitative behavior of the results (e.g., how hits are returned or that omitting a motion vector turns the sweep into a pure overlap test), leaving the agent without meaningful context about the outcome.

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 single sentence is concise and readable, but it is also under-specified: it largely restates the tool name 'cast_shape' with the additional gloss 'sweep test in physics space'. It is appropriately short, though not genuinely informative on its own.

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?

Given the read-only annotations, a rich input step, and the existence of an output, the description meets the minimum viability but fails to close the most important gap — telling the agent why this tool exists among physics siblings like godot_cast_ray_3d. It also does not mention the stationary-overlap behavior when motion is omitted, which the schema communicates but the description should echo.

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 for the description text is 0%, and the description names none of the six key inputs (origin, motion, shape_type, shape_params, max_results, collision_mask). Since coverage is far below the 50% threshold, the description bears the burden of explaining parameters and does not; the input schema itself does contain per-field descriptions, which partially rescues the agent.

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 action ('Perform'), the resource ('3D shapecast'), and the domain ('physics space'), adding the parenthetical '(sweep test)' to clarify what a shapecast means. It does not, however, distinguish itself from the closest sibling godot_cast_ray_3d beyond the obvious name difference, so it stops short of a 5.

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?

There is no guidance on when to use a cast shape instead of a ray cast, and no mention of when to provide a motion vector versus leaving it null for a stationary overlap test. The agent must infer the selection logic and invocation pattern entirely from the tool name and schema.

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