make_drawing

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

With no annotations, the description carries the behavioral burden and does so well: it discloses the on-disk side effect, that the drawing is closed unless drawing_path is supplied, that the title block is auto-filled from properties(), and warns to check overall dimensions on assemblies. It does not cover prerequisites such as requiring an activated document or expected runtime, so it stops short of a 5.

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?

Front-loaded with the outcome ('2D drawing ... → PDF for the shop floor') before any detail, then a tight Args list where each line adds distinct semantic value. The opening paragraph is dense and parenthetical-heavy, which costs a point on readability, but nothing is redundant.

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 geometry-generation tool with an output schema, the description covers the pipeline (generate → save → verify by reading the PDF), the per-parameter conventions, and the caveat about dimension accuracy on assemblies. An agent could invoke this correctly without opening the schema.

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 14%, yet the description documents six of the seven parameters with real semantics the schema lacks: view ordering and placement conventions ('top placed below', 'iso shaded, half scale'), scale encoding ('0 = largest standard scale that fits; 0.2 for 1:5'), template formats including full .idw paths, and the flat-pattern switch. Only 'instance' is left to its own schema description, which already covers it.

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 and artifact: produce a 2D drawing of the active part/assembly and save it to disk as a PDF. It also enumerates the contents of the output (base view, projected views, dimensions, title block), so the agent knows exactly what the call yields versus siblings like export_document or flat_pattern.

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 context is implied rather than stated: 'check them on assemblies' and 'flat: Sheet metal part' tell the agent when certain modes apply, and 'Read the PDF back to check the layout' hints at a verification loop. But no sibling is named as an alternative (e.g. export_document, flat_pattern), and no explicit when-not-to-use condition is given.

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