Build Walls from CAD

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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds real value: everything lands in one undo entry, dimensions are mm, and rejected joins are surfaced as unjoinedEnds/unjoinedReasons with dry_run parity. It still omits that a repeat run creates duplicate walls rather than being idempotent, and says nothing about permission/auth needs.

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?

Two tight sentences with the outcome and the join/dry_run contract front-loaded; no filler. The first sentence is slightly telegraphic ('Bridge openings, pair parallel CAD lines') but still earns its space.

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 13-parameter destructive mutation, the description covers only join/dry_run/units and leaves the majority of inputs, the effect on existing geometry, and error conditions unexplained. The output schema presumably covers returns, but the call contract itself is under-specified.

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 only 8% across 13 parameters, and the description explains just two of them (join, dry_run) plus a global mm unit. Core inputs like cad_id, layers, level, wall_type, max_gap_mm, thickness bounds, and response_timeout_s get no added meaning, so it does not compensate for the coverage 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?

The description states a concrete verb and resource ('pair parallel CAD lines and join basic walls', 'Bridge openings') that an agent can distinguish from the single-wall sibling revit_create_wall. It is clear what the tool produces, though it never explicitly names the sibling it replaces.

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?

Usage is implied by the CAD-line pairing workflow and the join/dry_run notes, but nothing states when to prefer this over revit_create_wall, revit_link_cad, or revit_execute_code, nor any prerequisite (e.g. the CAD must already be linked, layers must exist).

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