dimension_edit

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

No annotations are provided, so the description must carry the behavioral load, and it does substantively: batch items run in order, the first failing item halts the batch with no regeneration, regenerate defaults to true for set/set_text, destructive actions require an exact confirm token, and edits are not persisted unless an explicit save action is used. The gaps are the mechanics of obtaining the confirm token and what the failure response looks like, but the mutation profile is far better disclosed than typical.

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?

Roughly half the text is server-wide boilerplate irrelevant to dimension editing: feature/list visibility, layer/show semantics, ALL_* selector tokens, feature/suppress with_children, and export_image units. The genuinely relevant content (batch semantics, regenerate defaults, confirm requirement, action list) is split across three sections and not front-loaded, forcing the reader to sift.

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 four-variant, batch-capable mutation tool with no annotations and no output schema, the description covers batch ordering, failure abort behavior, regeneration, and the confirm requirement. It still omits what a call returns and how success/partial-success is reported, and the irrelevant bulk dilutes the coverage rather than extending it.

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 description coverage is 100%, so per-parameter documentation is already handled by the schema and the baseline is 3. The description adds real meaning on top — values are interpreted in model units, list items execute per-item in order with a single regeneration on full success, and regenerate's default is true for set/set_text (a default the schema does not state) — but it adds nothing for copy's to_file/to_name or show's path/assembly.

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 trailing action list gives a concrete verb+resource for each mode (set a dimension value, set dimension text, copy a dimension, show/hide a dimension), so the four variants are distinguishable. However, the opening paragraphs describe server-wide scope (already-open Creo, CREOSON limits, extrude/hole/round, layer/show, interface/export_image) and bury the tool's actual purpose, so it takes work to tell what this tool itself does.

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?

There is implied guidance — values are in model units, dimensions are never assumed by name, and geometry creation should go to extrude/revolve/hole/round instead — but none of that routes the agent between this tool's own modes or toward siblings like list_dimensions or model_export. Nothing states when to prefer copy over set, or when show is appropriate, so the agent must infer the use case.

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