budget_fab_order

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely useful context beyond that: no network, no keys, stdlib-only, deterministic offline math, and that the manifest is SHA-256 tamper-evident over the manufacturing artifacts. It does not mention currency, pricing-accuracy caveats, or how the cross-vendor recommendation is decided.

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?

A single dense sentence that front-loads purpose (cost budget + submission manifest) and then the differentiators (offline, no keys, stdlib-only, environments). No filler or restatement of the tool name.

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 10-parameter tool with a nested artifacts object and no output schema, the description covers inputs and execution environment well but says nothing about the returned structure — what the budget object contains, currency/units, or what the manifest looks like. The agent knows what it will compute but not what it will receive.

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 100% with defaults and enum-like value lists on every field, so the schema carries most of the load. The description still adds framing by enumerating the cost dimensions (layers, quantity, area, finish, SMT, shipping, lead priority) that correspond to parameters, and it flags the artifacts object as the manifest input — meaningful for the one nested parameter.

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 concrete verbs and resources: offline cost math over public price ladders (layers, qty, area, finish, SMT, shipping, lead), cross-vendor recommendation for JLCPCB/PCBWay, and a SHA-256 tamper-evident manifest over artifacts. An agent can tell it produces a budget plus an order-staging manifest. It stops short of naming the obvious sibling, calculate_fab_cost, so the boundary with that tool is left implicit.

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 an implied context — 'for CI order staging', offline/no-network on a laptop or Docker runner — which tells the agent this is a pre-submission estimation step. But it never states when to prefer it over calculate_fab_cost or the export_*/validate_* siblings in the same family, and there are no explicit exclusions.

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