Kz Room Geometry

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

No annotations are supplied, so the description carries the full burden, and it discharges much of it: it discloses that results are computed quantities (margins applied to doors, windows excluded from free segments, area excluding floor objects), which tells the agent the values are derived rather than raw stored data. It never states outright that the call is side-effect free, nor what happens for an unknown room, which keeps it below 5 for a tool with zero annotation coverage.

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?

It is one sentence with the resource front-loaded and each clause contributing distinct information; nothing is filler. The deep parenthetical nesting (openings, then free segments with margin and exclusion rules) makes it dense to parse but not verbose.

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?

An output schema exists, so the heavy enumeration of return fields is partly redundant, but the extra detail about margin and exclusion semantics is not recoverable from the schema alone. Combined with the note that the room may be addressed by name, type, or id, the definition is sufficient to call the tool correctly; only error behavior for a missing room is left open.

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% and the single 'room' parameter has no schema description, so the description must compensate — and it does, by revealing that the parameter accepts a name, a type, or an id. That is meaningful resolution information the schema alone does not give. It does not clarify how ambiguity between the three forms is resolved, so not a 5.

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 names a specific resource (geometry of one room) and enumerates exactly what that geometry comprises: interior contour edges with length, inward normals, load-bearing walls, opening abscissas, free segments, door swing zones, total and usable area. This distinguishes it clearly from the setters and mutators among the siblings (kz_set_room, kz_add_opening, kz_add_walls). It stops short of 5 only because it is a noun phrase with no explicit verb ('returns'/'computes'), leaving the retrieval nature implied rather than stated.

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 call this rather than kz_check_room, kz_summary, or any other read-oriented sibling, and no stated prerequisites. The parenthetical '(nom, type ou id)' tells the agent how to address a room, not when this tool is the right choice.

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