Shape add arch

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

Annotations already declare this is a non-readOnly, non-destructive, non-idempotent creation operation, so the safety bar is largely covered. The description adds genuinely useful behavior beyond that: units are metric, rise defaults to span/2, defaults exist for start/center/z_base, and the shape must subsequently be exported via shape_export_geom or shape_export_obst. It doesn't address what happens on duplicate/repeated calls, which the non-idempotent hint implies.

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?

Long but dense and front-loaded: the identity of the shape comes first, then the geometry math, then placement, then the required follow-up export, then units. Each clause carries information, though the parenthetical synonyms (arched/vaulted/semicircular, barrel vault, dome-roof tunnel) are slightly redundant.

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 creation tool with no output schema, the description supplies the geometric model, defaults, units, placement semantics and the mandatory next-step export call. The main residual gaps are the remaining cosmetic/identity parameters (name, color, surf_id) and any mention of resulting object identity, which is minor.

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?

With 75% schema coverage the baseline is 3, but the description adds real geometric meaning beyond the schema: rise = span/2 → semicircle, smaller → segmental arch; z_base = springing line (0 = floor, wall-top for a room); start/center defined as axis and transverse coordinates. It leaves name, color and surf_id unexplained, but those are self-explanatory or schema-covered.

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 (add) plus a precisely defined resource: an arched/vaulted/semicircular ceiling shell with span, rise, length and axis. It distinguishes itself from the sibling primitive-composition route ('instead of composing primitives') and from the export siblings it hands off to, so an agent can select it without opening a 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 an explicit trigger condition ('use this whenever the user asks for a round/arched/curved/semicircular ceiling or tunnel roof') and names the alternative approach (composing primitives). It does not spell out when-not to use it (e.g. vs shape_add_cylinder for a solid curved mass), so it stops short of full routing guidance.

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