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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description goes further by disclosing the exact computation (Table 5 areas per AWG, Table 4 area × 53/31/40% depending on conductor count) and the unusual rounding rule (round up only at .8 or more). These are real behavioral facts an agent could not infer from structured fields, though the response shape is only listed, not described.

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 purpose and outputs, then the formula, then the limits — a logical order with no filler sentences. The partial AWG table (six values followed by an ellipsis) is slightly bulky but each listed constant is directly usable, 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?

For a 12-parameter, zero-required calculator with no output schema, the description covers inputs (wire types, conduit types), the governing rules, and the five result fields it returns, which is enough to call it correctly. Residual gaps are minor: no statement of units/format for the returned values or how percentages are reported, and no guidance on the all-defaults case.

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% with per-parameter descriptions and defaults (count_14 defaults to 6, others 0), so the schema already carries parameter meaning and the baseline is 3. The description adds the wire-area constants and the THHN/THWN-2 restriction on wire type, but says nothing about the count_1 vs count_1_0 distinction or enum coverage for size/conduit.

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 (conduit fill for THHN/THWN-2 in EMT or Schedule 40 PVC) and enumerates the concrete results returned: total wire area, percent fill, fit verdict, smallest conduit, max same-size wires. That scope cleanly separates it from calc_box_fill, calc_wire_size, and calc_voltage_drop.

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 description implies when to use it (sizing conduit for a given wire complement) but never states when not to use it or points at the neighboring calculators. There is no rule such as 'use calc_box_fill for box capacity' or 'use calc_wire_size for ampacity' to route the agent among ~50 calc_* siblings.

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