line_of_sight

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

With no annotations, the description carries the full burden and does well: it discloses that object names resolve to bounding-box centres, that the two named objects never block the ray, and that the first blocker is returned. This is exactly the kind of caveat an agent needs to interpret results, though the return value when nothing blocks the ray is unstated.

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 tight sentences front-loaded with the core question, then parameter semantics, then the blocking caveat and usage. Every sentence earns its place.

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 two-param query tool with no output schema, the description covers inputs, the blocking rule, and the primary return. The only gap is the outcome when the ray is unobstructed, which is left to inference.

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 coverage is 0%, so the description must compensate, and it does: both parameters are explained as either a world point or an object name (bounding-box centre). The array shape for a world point is left implicit, but the semantic meaning is fully conveyed.

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 predicate (visibility between `a` and `b`) with the resource form (world point or object name). It is clearly distinct from the map-level siblings (sightline_map, viewshed), though it never names them explicitly to sharpen the boundary.

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?

'Use it for sight lines, cover and corridors' gives implied usage context, but there is no when-not guidance and no routing to alternatives like raycast or sightline_map despite the crowded sibling set.

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