create_reference_plane

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

With no annotations, the description carries the full burden and does disclose key behavior: it adds a feature to the tree, its returned name feeds create_sketch, angled planes error, and zero offset is rejected. It does not cover failure modes, permissions, or mutation reversibility, but for a feature-creation tool with an output schema the coverage is strong.

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 core action, then downstream usage, then explicit exclusions. Every sentence earns its place by adding a constraint or a routing hint rather than restating the name.

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 explained, and the description covers purpose, downstream integration, and both limitations. Nothing an agent needs to invoke it correctly is missing.

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 100% and the nested parameters (reference, offset, angle, flip) are already documented in the schema, including the same zero-offset and angled-plane caveats. The description therefore duplicates rather than adds; baseline 3 is correct.

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 reference plane offset from an existing plane or planar face') and distinguishes itself from siblings like create_axis and create_reference_point by its offset-from-reference behavior. The agent can tell what it produces and from what input without opening the schema.

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?

Explicitly names the alternative ('Use offset for parallel planes') and the excluded case ('Angled planes are not supported... needs a second reference this tool cannot take'), plus a hard precondition (offset of zero is rejected). It also ties the output to a downstream tool (create_sketch). This is as close to when/when-not/alternatives as a tool description gets.

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