cad

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so safety is covered. The description adds genuinely new behavioral context beyond the annotations: 'Committed mutations are rollback-able session steps' and that stop_on_error halts a batch at the first failure. It still doesn't say what a mutation can destroy or what permissions are needed.

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-loads the purpose, then the obj_name/obj_properties rule, then the rollback note, then an Args list. Nearly every line earns its place; the Args block mildly restates what the opening sentences imply but stays compact.

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 need not be described, and annotations cover the safety profile. For a 23-operation mutation tool the definition supplies the key invocation rules (object semantics, batch error handling, rollback-ability) and delegates operation details to operation_help; only doc_name is left unexplained.

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?

With schema description coverage at 0% and 8 parameters, the description must compensate, and it largely does: it explains obj_name (base object, or new object for loft/sketch/variables/datum_plane/hull), obj_properties (where params go), obj_type, ops, stop_on_error, and description. Only doc_name and operation lack prose, and operation is a self-evident enum.

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 concrete verb and resource ('Run one CAD modeling operation') and adds a role label ('the unified mutation entry point') that separates it from the read/inspect siblings like get_objects, get_view and measure_geometry. It stops short of explicitly contrasting with execute_code or session, so sibling differentiation is only partial.

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 is implied rather than stated: it routes the agent to operation_help('<operation>') for operation-specific guidance and clarifies which ops treat obj_name as new vs. base. There is no explicit when-to-use-this-vs-execute_code/session guidance or when-not condition.

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