edit_parts

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 real behavioral traits: preview-by-default, single-undo-step semantics on commit, and the max_force_scale=1 default for prebuilt engines. It omits permission/error behavior, but the transaction and default-mode disclosures are substantive.

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 core purpose and default mode before the op enumeration, and every sentence carries semantic content. Density is high and it reads as a run-on telegraphic block, but little is wasted.

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 complex 10-op discriminated-union mutation tool with no annotations, no output schema, and 0% schema coverage, the description supplies the key op semantics, selection fields, and commit behavior an agent needs. It is close to complete, with minor gaps only in return/error behavior.

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 largely does: select={ids/bounds/name/definition}, delta in blocks, count as additional copies, rotate via matrix or r-string plus pivot, mirror via axis/plane, and the Part fields (definition, position, rotation, mirror 1/2/4, color, name, settings). The telegraphic op-list covers most operation parameters, though top-level design/commit/revision get only brief treatment.

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+resource ('Atomic part edits') and immediately pins down its operating mode ('defaults to preview only'), so an agent knows this modifies parts in a design. It names the full op set but does not differentiate itself from siblings like edit_connections beyond the resource name.

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?

Gives workflow context ('Pass the revision from query_parts', 'commit=true keeps one undo step'), which implies the preview-then-commit flow. However it never states when to use this tool versus edit_connections or other edit siblings, and gives no explicit exclusions.

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