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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the free tier (2 calls per caller per UTC day), the $0.50 USDC x402 price, per-item billing for lists, and that pdf: true attaches a calculation sheet. It does not describe the shape of the returned verdict beyond 'pass or fail' and 'derated ampacity with its table', which is the main remaining gap.

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 opening sentence front-loads the purpose well, but the middle is a dense run-on mixing mode selection, pricing, and a verbatim copy of the input object shape that already appears in the schema. The free-allowance rule and the $0.50 rate are effectively restated in two places, and the inline schema blob is redundant rather than additive.

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 tool with nested objects, no output schema, and a paid/free split, the description covers purpose, alternatives, billing, and the nested input shape. What it lacks is any statement of the response structure (field names for the fill verdict or ampacity table) and error behavior for invalid widths or cable combinations.

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 a 3 is the baseline, but the description adds real meaning on top: width must be 'a width the table lists', covered/layout enums are paired with their valid values, and full/pdf/items are tied to their billing consequences. It stops short of explaining units or defaults for depth, ambientC, mv/kv, or the cables array fields beyond their names.

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 (NEC cable tray fill per 392.22 and cable ampacity per 392.80) with the exact code tables cited, and explicitly names the two siblings it is not (conduit_fill for raceways, design_cable for single-cable IEC ratings). An agent can route correctly 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 explicit alternative routing (conduit/raceway → conduit_fill, single-cable IEC → design_cable) plus the mode selection rule: omit full for the free verdict, set full: true or make any paid call for the complete answer, and use items instead of input for a batch. Exclusions and preconditions are stated rather than inferred.

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