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

Annotations already declare read-only, idempotent, non-destructive, so the safety profile is covered; the description uses its space to disclose actual behavior instead. It enumerates the specific refusal conditions — untrusted factory, terms hash mismatch, payTo not matching terms, amount/asset mismatch, payer mismatch, expired terms, closed window, window without referee — which tells the agent exactly what can fail and why, well beyond structured fields.

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 when-to-use trigger is front-loaded in one sentence, followed by the behavioral detail and a closing safety statement ('Read only'). Every clause in the refusal list names a distinct failure mode and earns its place; nothing is repeated from the annotations or schema.

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 read-only validator with five parameters (one required, nested objects) and no output schema, the description covers purpose, preconditions, and failure modes thoroughly. The remaining gap is the success path: it never says what a passing result contains (the recomputed address? a boolean?) or whether a refusal raises an error versus returning a status, which matters when there is no output schema to consult.

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 already 100%, so the baseline is 3. The description adds real meaning on top by labeling the optional payload check as validating the signed EIP-3009 authorization's to, value, and from — tying payload sub-fields to a concrete verification. It does not clarify maxAmount or how requirements relates to extensions, so it sits just above baseline.

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 specific verb and resource — it recomputes the payment address from a 402's terms against IFSO's v2.1 factory before the user signs. The opening sentence ('Run before signing a 402 that carries the ifso-conditional extension') positions it precisely against the sibling family (prepare_x402_conditional, explain_payment, get_payment) by naming the artifact it consumes and the moment it runs.

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 context is explicit: call it before signing, and only for 402s carrying the ifso-conditional extension. That is a clear when-to-use condition. It stops short of naming the alternative (e.g., 'if you have not yet produced the 402, use ifso_prepare_x402_conditional first') or stating when the check is unnecessary, so no exclusions are given.

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