room_load_scan

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

With no annotations, the description carries the full burden and does so well: it discloses that units and up-axis are detected from geometry and 'never trusted from file metadata', that raw scans are less precise and carry +/- and confidence, that corrupt/empty files return an error with a code and hint, and that no option is remembered. These are exactly the behavioral traits structured fields do not provide.

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?

Long but dense and front-loaded: purpose first, then path, then per-parameter guidance, then a STATELESS block and caveats. Most sentences earn their place, though the format-support sentence is somewhat sprawling and could be tightened.

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 return values need not be re-explained, and the description covers the remaining complexity for a 7-parameter loader: detection heuristics, override vs auto semantics, calibration, error behavior, and cross-tool handoff. Nothing essential an agent needs to call it correctly is missing.

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 explains most parameters: path, scan_units/up_axis as overrides, north_deg with its frame convention, and known_dimension with a concrete object shape. The supported-format prose implicitly maps the format enum. The 'units' parameter (metric/imperial/both) is never explained, leaving one gap.

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 verb+resource ('Read a room scan') and enumerates exactly what it reports (walls, doors, windows, objects, size, detected units and up axis). It also situates itself relative to siblings by naming room_list_walls and referring to 'the other room_* tools', so an agent can tell it is the loader rather than a query tool.

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?

Gives clear operational context: pass scan_units/up_axis 'only to override', use known_dimension to calibrate, and note that scans with no compass cannot resolve 'north wall' references. The STATELESS note tells the agent to carry load_options forward to other room_* tools. It stops short of an explicit when-to-use/when-not statement versus room_summary or the other room_* readers.

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