creo_create_project_general_sketch

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

Annotations only mark destructiveHint=true, but the description substantially extends that by disclosing duplicate-name rejection, degenerate-geometry rejection, per-entity verification, regeneration, volume-unchanged validation, save behavior, older-version Recycle Bin handling, and partial-sketch deletion on failure. This fully informs the agent of side effects and failure semantics.

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 the verb and resource, and every sentence contributes material behavioral or input information. The first sentence is long and dense, but it is still economical rather than rambling.

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 7-parameter mutation tool with no output schema, the description covers expected model, plane requirements, geometry limits, validation, regeneration, save, recycle-bin cleanup, and rollback behavior. It does not describe return payloads or the coordinate semantics of entity properties, but the schema property names and ranges provide reasonable coverage there.

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 86% and several parameters already have inline descriptions, so baseline is 3. The description adds useful meaning by linking expected_model to the 'current expected Creo project part,' clarifying sketch_plane and orientation_plane as named datum planes, and defining entities as 1-32 lines/circles/arcs with duplicate-name rejection.

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 ('Create') and a precise resource ('one independent sketched datum-curve feature'), and bounds the geometry to '1-32 lines, circles, and arcs on a named datum plane with an explicit orientation plane.' This makes it easy to distinguish from the many copy-style sibling tools even though no sibling is named explicitly.

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 gives strong operational context—current expected model, plane requirements, validation, and save behavior—so an agent can infer this is the direct sketch-creation tool. However, it never states when to prefer this over the numerous create_safe_* or create_project_* alternatives, nor does it provide exclusions.

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