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

Goes well beyond annotations: flat $0.01 pricing, refusal semantics that are free, result ordering (one per-leg object in request order), and the x402 payment dance (call without payment to get the challenge, retry with _meta["x402/payment"]). The one slight tension is readOnlyHint=false on what is semantically a validation read, but that is plausibly justified by the payment side effect, not a real contradiction.

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 the core purpose and price, then constraints, then payment mechanics. Dense but every sentence carries information; the payment/HTTP-equivalent block is the longest and least essential to tool selection.

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 no output schema, the description covers return shape (one per-leg object, request order) and all refusal/pricing behavior; with an open-world paid tool, the payment flow and preflight are exactly what an agent needs. Nothing material is missing.

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%, so baseline is 3; the description adds real meaning by explaining that legs must be 2-3 (reinforcing minItems) and that a 1-leg call is rejected, plus that extra state is needed for the us leg. It stops short of explaining any other field, but the schema carries that.

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+resource ('fan one structured address out to 2-3 live legs') with the exact leg codes, and implicitly separates itself from address_leg_nl/address_leg_us via the 1-leg refusal guidance. An agent can tell exactly what this does and how it differs from the single-leg 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?

Explicit routing: 1-leg requests refuse — 'use the leg tool instead'; Canada is only available in this bundle; unavailable legs (nz, es) refuse the whole bundle; free pre-check endpoint given. When-to-use, when-not, and alternatives are all stated.

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