sheet_metal_edge_flange

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

With no annotations the description carries the full burden and does so: it discloses the preview-API dependency and the FUSION_API_ERROR reason=api_unavailable no-op path, states that failing flanges are rolled back, maps each invalid input to INVALID_PARAMS, and names the stale-ref hazard.

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-loaded with the one-line purpose, then constraints, ref warnings, error mapping, return shape, and a concrete example, each in short discrete segments. Every sentence adds new information; nothing restates the title or schema verbatim.

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 12-parameter mutation tool with no annotations and no output schema, the description covers invocation constraints, ref sourcing, rollback semantics, error reasons, and even the return value shape. An agent has enough to call it safely and to interpret failure.

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%, so the baseline is 3; the description adds real meaning by stating the mutual exclusivity of height and to_entity, the single-edge restriction on to_entity, and the ref lifecycle (refs change after each flange). It does not elaborate on width variants, to_offset, bend_position, or height_datum beyond the schema text.

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 and resource ('bend up a wall from linear edges of a sheet metal body') and scopes it against a non-tool alternative: sketch-line bends are unavailable, so an edge flange is the way to add a bend. An agent can tell this apart from generic feature tools without opening the schema.

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 explicit invocation prerequisites and exclusions: exactly one of height/to_entity, refs taken from inspect_query on the latest body and re-taken after every flange because refs change, a single edge for to_entity, and a capabilities check before use when the preview API may be missing.

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