calligraphy_preflight_audit

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose useful traits: determinism of the quote, concrete price anchors ($149 to $1,495+), surcharge percentages for rush (+35%) and ECO (+50%), and supported input formats. It never states whether the call is read-only or whether it persists a job/quote server-side, and gives no permission, rate-limit, or quote-validity context.

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 core purpose is front-loaded in the first clause, and the mode instructions follow in a logical order. It is dense with internal jargon ('3-Lever NRE-anchored', 'vibe_micro', 'route_3d') and heavy parenthetical nesting, which costs some readability, but for a 9-parameter tool the length is largely justified.

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 9 parameters, zero required, no annotations, and no output schema, the description should do more than it does. It never says what comes back (readiness report? quote breakdown?), whether sample_id overrides project_path if both are passed, or what happens with an empty call, and the requested_sku enum is mostly 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 78%, so the baseline is 3, but the description adds real meaning by mapping parameters to transport modes (project_path only in stdio; pcb_text + filename or upload_b64 for remote) and by enumerating the three valid sample_id values. It still leaves requested_sku semantics thin, only tying two SKU names to prices and giving no guidance on the other five enum values.

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 first sentence names concrete verbs and resources: inspect a .kicad_pcb file or .zip bundle, verify outline/pad readiness, and return a deterministic NRE-anchored price quote, with the price band spelled out. An agent can tell this is an audit-and-quote tool rather than a pure analysis tool like analyze_kicad_pcb. It stops short of explicitly naming any sibling it differs from, so it lands at 4 rather than 5.

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 Mode A / Mode B split gives explicit conditions: use sample_id for a zero-file demo, project_path for a local board in stdio mode, or pcb_text/upload_b64 for remote HTTP. That is clear routing guidance for the input channels. It does not tell the agent when to prefer this over audit_pcb_dfm_rules or analyze_kicad_pcb, and it does not say what the default is when no parameter is supplied.

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