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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that payment history is kept, only the saved entry is removed, and that the operation is not reversible through the API. It also notes that parameters can be sent in the body or query string. This is adequate though it does not explicitly state success/failure outcomes or idempotency.

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 description is front-loaded with the core purpose in the first line, followed by essential behavioral and usage notes. It is appropriately sized, though the '(free)' suffix is cryptic and could be removed. The structure flows logically from purpose to behavior to guidance, with no unnecessary filler.

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 destructive, irreversible operation, the description covers the key aspects: what is removed, what is preserved, and the recommended alternative. It also addresses the transport flexibility. It does not mention behavior for non-existent recipients or error cases, but given the schema and lack of output schema, it is reasonably complete for an agent to call it correctly.

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?

The input schema already describes all three parameters with 100% coverage, including the enum for platform and the explanation for recipient_id. The description adds a minor usage note that platform and recipient_id may be sent in the JSON body or query string, which is a transport detail rather than deeper parameter semantics. Given full schema coverage, the baseline of 3 is appropriate.

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 clearly states the verb 'Remove' and the resource 'saved recipient' with explicit mention of Venmo or PayPal. It distinguishes from sibling delete tools like delete_banking_recipient and delete_address_book_entry by specifying payment recipients, and from update_payment_recipient which modifies rather than removes. The parenthetical '(free)' is ambiguous but does not undermine the core purpose.

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 description explicitly provides when to use the tool (to remove a saved recipient) and when to prefer an alternative: 'prefer archiving (`POST /payment-recipients` with `archived: true`) when the account owner may want the recipient back'. It also advises confirming before removing someone not asked to remove, giving clear conditional guidance.

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