sw_create_drawing

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the agent knows this is a non-destructive mutation. The description adds useful ordering context around sw_set_properties and sw_export, but it does not say whether a new drawing document is created, whether an existing drawing is overwritten, or where the result is saved. With annotations covering the safety profile, a 3 is appropriate.

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 short sentences with the output composition front-loaded and the prerequisite/follow-up guidance second. There is no filler. The first sentence is a fragment ('A drawing of...'), which is slightly less direct than an explicit verb-first statement.

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 an 8-parameter creation tool with no output schema, the description gives the essential workflow but omits important context: whether a new drawing file is created, how existing drawings are handled, and what the caller gets back. It is adequate to initiate a call but not fully complete.

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 description coverage is 75%, with enum values and descriptions for bom, paper, scale, views, standard, and dimensions already in the schema. The description mentions the concepts behind those features (views, isometric, dimensions, BOM) but adds no syntax, defaults, or behavioral detail beyond the schema. Baseline 3 is correct here.

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 what is produced: a drawing containing three standard views, an isometric view, dimensions, and a BOM for a saved part/assembly. This is clear enough to distinguish it from export or view-insertion siblings, though it never uses an explicit verb like 'create' and doesn't explicitly contrast with sw_add_drawing_view.

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?

It provides concrete workflow guidance: fill the title block with sw_set_properties on the model first, then export with sw_export. This tells the agent the prerequisites and the downstream step. It does not explicitly state when not to use this tool or how it relates to sw_add_drawing_view, so it stops short of a 5.

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