Architecture: Stair

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

Annotations only supply destructiveHint=false, so the description carries the burden and does so well: it discloses label placement (2.5 mm × scale), the Blondel rule semantics (2R + G against 600-650 mm, reported not enforced, ok:false rather than refusal), and a precise pre-draw refusal list including stair-id collision and geometry constraints. This is exactly the kind of behavioral context annotations cannot express.

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 what is drawn, then constraints, then refusals — a sensible order. It is on the verbose side (four dense paragraphs), but nearly every sentence carries a distinct constraint or rule, so little is wasted.

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?

With 12 parameters, 7 required, and an output schema present, the description need not restate return values, and it does supply the refusal conditions and the one notable reported value (blondel). It stops short of stating units/coordinate assumptions beyond what the schema already documents, but nothing critical for a correct call is missing.

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 the baseline is 3, but the description adds real meaning beyond the schema: it explains the riser-count minimums (2 straight, 4 for L/U, two per flight), the relationship of risers/going/riser_height to the reported Blondel value, and that the label scales with the scale parameter.

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 description names a specific resource and the exact geometry produced: 'A stair in plan: every riser as a line, the outline, the walking line with its arrow.' An agent can immediately distinguish this from siblings like arch_wall, arch_opening, or entity_create_line 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?

Usage is implied by the refusal list ('Refused before anything is drawn: ...'), which tells the agent what inputs are invalid, but the description never states when to reach for arch_stair versus alternatives such as arch_plan_from_spec or arch_catalogue_insert. No positive when-to-use guidance or alternative routing is given.

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