add_dimension

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

With no annotations present, the description must carry the burden of disclosing behavioral aspects. It mentions that parameter-name expressions propagate when parameters change and that literal mm creates a baked value, which indicates parametric vs. non-parametric behavior. However, it does not state whether the operation is read-only, modifies the document, or has other side effects, leaving a gap in transparency.

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 description is succinct yet dense with useful information. It begins with a core purpose, then systematically explains behavior and parameter relationships. Each sentence adds value without redundancy, making it easy to parse and apply.

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?

The description covers essential usage details, including the gotcha about expressions and baked values, which is critical for correct usage. It also clarifies entity requirements per kind. While it omits explicit explanations for 'sketch' and 'text_pos', these are likely inferred from the schema and typical CAD workflows, so the overall completeness is high.

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?

The description provides detailed semantics for the 'kind' parameter and how it shapes the 'entities' parameter (e.g., 2 point refs for distance, 2 line refs for angle). It also explains the 'expression' parameter. However, it does not elaborate on the 'sketch' or 'text_pos' parameters, which are left mostly unexplained beyond schema titles. Coverage is good but not complete.

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 clearly states the tool's purpose: adding a dimension with an expression. It also lists the supported kinds (distance_h, distance_v, distance, angle, radial, diameter), making the scope unambiguous and distinguishing it from other tools like drive_joint or extrude.

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 practical usage instructions, such as how to use parameter-name expressions versus literal values, and how entities depend on the kind. However, it does not explicitly mention when to prefer this tool over alternatives or provide context about typical usage scenarios, which weakens the guidelines.

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