Post Instances Payins Evm

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

Goes well beyond the annotations: discloses the return payload (payer instructions), the expiry constraint, the idempotency/retry contract, and non-obvious sandbox semantics (auto-complete ~30s after creation, request_amount 66600 fails, 77700 refunds). Those magic values and timings are unobtainable from the schema and are exactly the kind of behavior an agent needs. The idempotentHint=false annotation is not contradicted — the key makes retries safe rather than the endpoint being inherently idempotent — but this tension is worth noting.

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?

Four tight sentences, front-loaded with the action and return value, then the expiry and idempotency constraints, then the sandbox test values. Every sentence carries operational information; nothing is padding.

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 correctly covers the return (payer instructions) and the mutation's key behaviors, so an agent can call it correctly. Gaps remain around error/expiry behavior (what happens if the quote has expired) and the unexplained instance_id, but annotations and schema carry the safety profile.

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 only 33%: Idempotency-Key is well documented in the schema and the description reinforces its purpose, but instance_id and payin_quote_id carry no schema descriptions at all. The description implies payin_quote_id's role ('Creates a payin from a payin quote') but never explains instance_id, its 15-char format, or how the quote id is obtained, so it only partly compensates for the gap.

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?

Specific verb+resource: 'Creates a payin from a payin quote and returns the instructions the payer uses to send funds (for example a Pix code or bank details)'. This cleanly separates it from sibling PostV1InstancesPayinQuotes (creates the quote) and PostV1InstancesPayinsCardPayment (a different payin rail), and it states the return payload up front.

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 a concrete precondition ('Create it before the payin quote expires') and a retry rule (send an Idempotency-Key so a retry cannot create a second payin). It stops short of naming an explicit alternative or when-not-to-use condition (e.g. when to use the card-payment or EVM payin variant instead), which keeps it below a 5.

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