sheet_metal_refold

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

With no annotations, the description carries the behavioral burden and does so well: it discloses the preview-API dependency, names the failure mode (FUSION_API_ERROR reason=api_unavailable) and guarantees 'nothing changed' on failure. It also documents the INVALID_PARAMS condition for a non-UnfoldFeature ref. What it does not disclose is what state changes on success beyond the returned body lists.

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 core action is front-loaded in the first sentence, followed by short labeled blocks for the API caveat, error conditions, and return shape. No filler, though the return-key dump is a dense single line rather than a structured list.

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?

No output schema exists, and the description compensates by enumerating the returned keys (feature, health, created/modified/removed_bodies, rule). Combined with the documented failure modes and the capability prerequisite, an agent has nearly everything needed; the meaning of 'health' and 'rule' values is left unexplained.

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 single parameter is documented as 'UnfoldFeature ref from sheet_metal_unfold', so the baseline would be 3. The description adds validation semantics the schema lacks — that a ref which is not an UnfoldFeature yields INVALID_PARAMS — which earns an increment.

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 ('Refold the bends of an unfold feature'), which precisely defines the inverse of sheet_metal_unfold and lets an agent distinguish it from the unfold/contour_flange/edge_flange siblings. It stops short of naming the sibling it complements, so it lands at 4 rather than 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?

Provides one concrete prerequisite: verify with sheet_metal_capabilities first because the tool depends on the preview Fusion API. That is real routing guidance, but there is no explicit statement of when to prefer this over re-running sheet_metal_unfold or redoing the flat pattern, so usage context is only implied beyond the capability check.

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