Cast a ray from a start point to an end point and receive collision results, solving hit detection and line-of-sight queries.
Cast a ray and return collision results
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | End point {x,y} or {x,y,z} | |
| from | Yes | Start point {x,y} or {x,y,z} | |
| collisionMask | No | Collision mask. Default: 0xFFFFFFFF |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure, yet it only states the action and vaguely promises 'collision results.' It does not disclose the shape of the returned results, whether triggers are hit or only solid bodies, whether it returns the first hit or all hits, or that this is a read-only operation. The statement is accurate but drastically under-discloses behavior.
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?
Eight words, zero filler, front-loaded with the operative verb. The single sentence earns its place and correctly leaves parameter details to the schema rather than repeating them.
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 simple 3-parameter tool this is minimum viable: the schema covers all parameters and the description states the core operation. However, with no output schema and no annotations, the return contract ('collision results' is undefined — hit point? object reference? distance?) and the read-only safety profile are left unspecified, so an agent cannot fully predict what the tool will return.
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 100%: the schema already documents from, to, and collisionMask with point formats and a default value. The description adds no parameter-level information, but per the baseline rule for high schema coverage, a 3 is appropriate — the schema carries the parameter documentation burden.
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 specific verb ('cast') with a specific resource ('ray') and states the outcome ('return collision results'). This is canonical raycast terminology that an agent will immediately recognize, and it distinguishes the tool from all ~150 siblings, none of which perform raycasting.
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 description provides no guidance on when to use this tool versus alternatives. It mentions no exclusions, prerequisites (e.g., an active physics world), or when a raycast is preferable to other collision queries among the physics-related siblings (game_add_collision, game_physics_3d, game_physics_2d). The agent must infer usage entirely from the name and minimal description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.