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

Annotations declare destructiveHint=true, readOnlyHint=false and openWorldHint=false, and the description explains the destructive dimension directly: a precheck nobody starts is deleted with its files after 24 hours. It also adds traits annotations cannot express — the operation is free/never billable, it returns asynchronously within seconds, and cost past the plan is capped at start time via max_overage_cents. No contradiction with the declared write/destructive profile.

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?

Purpose and the free/non-billable guarantee are front-loaded, and every sentence conveys operational information. It runs as one long paragraph with several clauses chained together (metered_max, overage, polling, attach, start), which costs some scannability but no sentence is filler.

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?

There is no output schema, and the description compensates by enumerating what comes back: how the assembly splits into made/catalogue/excluded parts, how many calculations start, how many the plan pays for (metered_max) and the possible overage. Combined with the async polling contract and expiry rule, an agent has everything needed to call and follow up correctly.

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 schema already carries batch_id grouping, position ordering, drawing structure and the gzip/data-URI acceptance. The description restates the base64/gzip file convention and drawings but adds no new semantics for batch_id, position, part_number or content types; baseline 3 applies.

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 gives a concrete verb and resource — it previews what a CAD file's calculation will do before the calculation is started, and returns a breakdown of made parts, catalogue parts, excluded parts and metered counts. It also names the siblings that handle the follow-up steps (get_precheck for polling, attach_drawing for drawings, upload_and_quote for starting), so an agent can place it precisely among 18 tools.

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 spelled out with conditions and alternatives: send the STEP file as base64, poll with get_precheck while status is received, route unmatched drawings via attach_drawing with precheck_id and component_key, and start the calculation with upload_and_quote passing precheck_id and max_overage_cents. The 24-hour non-started expiry is an explicit consequence, not left to inference.

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