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

Goes well beyond the destructiveHint/idempotentHint annotations by disclosing the cascade: retiring an un-settled payment rolls the invoice status from 'paid' back to 'sent' and clears paid_at. It also explains the approval semantics that differ by caller type — agent calls park for human approval in the Simpler UI while human calls self-approve — which is critical information an agent cannot infer from any structured field.

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 approval requirement is bracketed and front-loaded, the destructive semantics come next, and the follow-up tool is last — each clause carries distinct information with no repetition. Dense but every sentence earns its place.

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 mutation with no output schema, the description supplies the side effects, approval gate, and follow-up action, which is most of what an agent needs. The gap is the unexplained parameter set — an agent still doesn't know what note, method, currency, or amount_cents do on a delete call.

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 description coverage is only 25% (just id and its payment_id alias), yet the description mentions no parameters at all — not the note, method, currency, invoice_id, occurred_at, or amount_cents fields, several of which are unexplained and odd for a delete operation. With 8 parameters and sparse schema text, the description needed to compensate here and does not.

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?

"Retires a payment fact row" names a specific verb and resource, and the parenthetical clarifies it is a soft-retire within an append-only ledger rather than a hard delete or an edit. It explicitly contrasts with the alternative correction path by naming invoice_payment_record, so it is distinguishable from the large family of invoice_payment_* siblings.

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?

States this is "the only correction lane" given payments are append-only and amounts are never edited, which tells the agent both when to reach for it and why no update-style sibling applies. The "NEXT: invoice_payment_record to re-record the correct amount" clause completes the workflow routing.

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