solid

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

Annotations only provide readOnlyHint=false, so the description adds valuable behavioral context: fillet/chamfer currently error out, and native edge edits reject volatile indices. The 'safe COM API' phrase hints at safer operations, and optional erase_profile? flags suggest deletion behavior. However, it does not disclose side effects like whether boolean subtract destroys inputs or whether extrude consumes the profile, so full behavioral clarity is still missing.

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 front-loaded with a one-sentence summary, then uses a scannable code-style list for each operation. No filler words; the fillet/chamfer warnings are directly relevant to operation selection. It is long but dense and appropriately structured for a multi-operation tool.

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 multi-operation CAD mutation tool with no output schema, the description thoroughly documents operation inputs but says nothing about return values or how resulting solids are referenced in subsequent operations (e.g., how primary_id or profile_id values are obtained). It also omits unit conventions or the need for an active drawing context beyond the doc_id parameter. The operation list is comprehensive, but the missing flow/return semantics 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?

The input schema has 0% description coverage — data is just an arbitrary object/null. The description compensates thoroughly by providing a field-level mini-schema for every operation, e.g., create_box {center, length, width, height, layer?} and boolean {primary_id, tool_id, operation}. This is exactly the meaning the schema lacks, even though generic parameters like doc_id and lease_token are left to the schema.

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 opens with 'Create and combine native AutoCAD 3D solids through the safe COM API,' which is a specific verb-resource pairing. The enumerated operations (create_box, create_cylinder, extrude, revolve, sweep, boolean) clearly distinguish this from sibling tools like entity or product, making it unambiguous that 'solid' is exclusively for native 3D solid modeling.

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 explicitly names product.rounded_box as an alternative for analytic radius geometry and warns that fillet_edges/chamfer_edges return capability errors until stable semantic edge selection exists. It also states that general native edge edits never accept volatile edge indices, providing clear when-not guidance and an alternative tool.

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