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

Beyond the destructiveHint=true annotation, it discloses concrete write behavior: it refuses a model already holding geometry unless replaceExisting is set, creates default material/sections/thickness where ids are missing, and records the run for undo. It also states what the preview returns (counts, metrics, groups, planHash), which the 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?

Two dense sentences, front-loaded with the generation capability before the preview/write semantics. Every clause carries information, though the first sentence is a long run-on list that would read faster split into capability and options.

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 destructive, no-output-schema mutation tool with a nested geometry object, the description covers the preview payload, the write preconditions, default-property fallbacks and the undo path. Nothing an agent needs to call it safely 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 coverage is 86%, so the schema carries most parameter documentation; the description adds value on top by naming the actual group labels (GIRDERS, CROSS-BEAMS, END-BEAMS, SPAN-n, DECK) that structureGroups produces and by tying apply/preview to the approval workflow. It adds less on individual geometry fields, which the schema already covers.

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 — generates a bridge deck as beam grillage or plate mesh — and names the engine (the plugin's own), the addressable features (skew, unequal girders, plan curvature, multi-span, crossfall, vertical profile) and the structure groups produced. An agent can distinguish it from siblings like bridge_reshape, culvert_build, or skew_grillage_undo 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?

The preview-versus-write split is explicit: without apply it only previews, with apply: true it writes, and the run is recorded for skew_grillage_undo. It does not explicitly name a sibling alternative for non-plugin deck creation (e.g. bridge_reshape), so it is clear context without full exclusion guidance.

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