set_dimension

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

No annotations exist, so the description carries the full burden and does: it discloses that a rebuild and remeasure occur, that broken_features names post-change failures, that refusals (equation-driven dimensions, size of 0) come with a reason, and critically that the part is left unchanged on refusal — atomicity semantics an agent cannot infer elsewhere.

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?

The core action is front-loaded in the first sentence, and the follow-on sentences each carry distinct information (failure handling, unit rules, refusal semantics). It is dense but disciplined; only the 'heart of the correction loop' framing is arguably decorative.

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-parameter mutation with no annotations and no output schema, the description covers units, name syntax, result structure (dimensions by role, broken_features), and failure/rollback behavior — everything an agent needs to invoke it correctly and interpret the response.

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 does: it explains dimension_name syntax ('D1@BlockExtrude'), that value_mm is millimetres for lengths but degrees for angles, that a point coordinate takes a sign (-5 being across the origin), and that sizes are refused below 0. This adds substantial meaning beyond the bare number/string schema.

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 ('Set a named driving dimension') with a concrete example name and the full effect chain (rebuild, remeasure). An agent immediately knows this is the parametric edit primitive, distinct from list_dimensions or set_equation.

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?

Positions the tool as 'the parametric edit at the heart of the correction loop' and instructs the agent to fix or undo broken_features before proceeding, which is real routing guidance. It also points to list_dimensions for units. It stops short of explicitly naming an alternative tool or a when-not-to-use case, so it lands just below the top band.

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