manage_sheet_metal_rules

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

With no annotations, the description carries the full burden: it does disclose that "set" mutates bend radius and unfold method (not just thickness), which is meaningful behavior beyond the schema. It omits whether the change is reversible, whether the active document must already be a sheet metal part, and what happens when a rule name is not found.

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 opening line establishes scope, then the set-vs-thickness recommendation is front-loaded before the Args block. The shop-naming aside ('T15-V10' = 1.5 mm sheet, V10 die) is illustrative rather than required, but it justifies how rule names are formed and is short enough to earn its place.

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 needn't be explained, but this is an unannotated mutation tool with 4 parameters and thin schema coverage. The description covers operation choice and units yet never states prerequisites (an active sheet metal document) or failure behavior for unknown rule names.

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 only 25% (only 'instance' is documented in-schema), so the description must compensate, and it largely does: it defines the three action values, marks name as case-insensitive and scoped to "set", and gives the unit (mm) for thickness. Only the 'instance' parameter and the list default are left to the schema.

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?

Names a specific resource (sheet metal rules of the active part) and enumerates the three supported operations (list/set/thickness), so an agent can tell it acts on rule configuration rather than geometry. It doesn't compare itself to siblings like add_flange or export_flat_pattern, which is the only thing keeping this below a 5.

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 instructs to prefer "set" over "thickness" and explains the difference: set applies thickness, bend radius and unfold method together, while thickness changes only thickness. That resolves the main selection ambiguity, but "list" is never framed as the discovery step preceding set, and no preconditions are given.

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