nx_create_roughness

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

With no annotations, the description carries full burden: it discloses the target scope (current sheet), the meaning and units of position, and how value is placed. It omits whether the operation fails without an active sheet, whether it is undoable, or whether value accepts non-Ra grades — relevant for a mutation tool with zero annotation coverage.

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?

Three short lines, front-loaded with the action, then the two pieces of non-obvious information (slot semantics, coordinate frame). No filler sentences.

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?

An output schema exists, so return values needn't be explained, but for a 3-parameter creation tool with 0% schema coverage the description should also state the preconditions (active drawing sheet) and whether the symbol can be updated or only created. Adequate but with clear gaps.

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 does for two of three params: value is mapped to the symbol's a1 slot with concrete examples ("1.6", "3.2"), and pos_x/pos_y are placed in sheet coordinates in mm. It doesn't mention the defaults (20, 20) or that zero params are required, leaving a small gap.

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 resource ("Create a surface finish (roughness) symbol") plus the scope ("current drawing sheet"), which is clearly distinct from annotation siblings like nx_create_note or nx_create_dimension. It stops short of explicitly naming how it differs from other drawing-sheet creators such as nx_create_title_block.

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 implies usage (drawing sheet context, sheet coordinates) but never says when to choose this versus nx_create_note or the dimension tools, and gives no prerequisites such as needing an existing/active drawing sheet. Usage is inferable rather than guided.

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