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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, destructiveHint=false, so the safety profile is largely covered. The description adds that it emits Stripe, Coinbase Pay (x402), and watch-only USDT/USDC payment instructions, implying a billable/order-like operation, but never states that a call may create a charge or async job, whether files uploaded are persisted, or how long a job runs.

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 and dense with no filler: alias statement first, then capabilities, then the two modes. The Mode A/Mode B sentences are long run-ons with parenthetical nesting, which makes them slightly harder to scan, but every clause carries actionable content.

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 7 parameters, no required fields, no output schema, and mutation semantics, the description carries a lot of weight. It explains how to supply input and what payment guidance comes back, but with no output schema it should say what a successful call returns (job ID? status URL? artifacts) and whether a separate status check is needed, and it leaves the SKU/email commercial parameters unexplained.

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 57%, and the description usefully explains the mode-selection parameters (sample_id values, pcb_text, filename, upload_b64 with accepted extensions), which is the main ambiguity. It says nothing about `requested_sku` (whose enum and default `route_3d` are undocumented anywhere), `customer_email`, or the ordering implications, so three billing-relevant parameters remain opaque.

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: "synthesize and route a PCB through Calligraphy EDA," plus quality targets (0 opens, 0 DRC) and the side effect of returning payment instructions. The one ambiguity is that it self-labels as an "Alias for calligraphy_compile_board" without saying why an agent would pick this alias over the named sibling, leaving the distinction unresolved.

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?

Concrete branching guidance is supplied: Mode A pass `sample_id='2l_rp2040'` (or the two other IDs), Mode B read a local board file and pass `pcb_text`+`filename`, or `upload_b64` for `.PcbDoc`/`.zip`. That is real when-to-use-which-path guidance, but it stops short of saying when to use this tool at all versus diagnostic siblings such as analyze_kicad_pcb, preflight_audit, or compile_board.

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