add_dimension

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

With no annotations, the description carries the burden and does disclose useful behavior: default side placement ('nearer the geometry'), default offset row progression (10, 18, 26 ...), and an explicit return payload of ids, values, boxes, and overlap warnings. It stops short of stating that this is a persistent mutation, whether it is undoable, or what error conditions exist.

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?

Dense but front-loaded: the core purpose is in the first sentence, followed by parameter semantics in a compact order. The telegraphic phrasing ('its centre; alone its diameter') occasionally reads like notes rather than prose, but no sentence is wasted.

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 7-parameter mutation tool with zero schema description coverage and no annotations, the description covers most of what an agent needs: accepted reference syntaxes, style/direction/side vocabularies, placement defaults, and return contents. The unexplained required 'view' parameter and absent error/prerequisite behavior leave a real gap.

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 largely does: ref formats ('edge:-x', 'hole:CBore1', 'feature:CornerFillet', model point [x, y, z]), to, style, direction, side, and offset_mm all get concrete value semantics and defaults. The required 'view' parameter is never explained — no format, no statement of what a view identifier is.

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 action and resource: adding a dimension in a view between references, or a size of one. The scope (single span vs. series) is enumerated. It does not explicitly distinguish itself from siblings like set_dimension, list_dimensions, or import_dimensions, so an agent must infer the difference from the verb alone.

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?

The description gives strong in-tool guidance for choosing a style ('single' with ref/to vs. 'baseline'/'chain'/'ordinate' with to=[ref, ref, ...] measured from ref) and sensible defaults for side and offset. However it never says when to use this tool rather than set_dimension or import_dimensions, nor any prerequisite such as requiring an existing drawing view.

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