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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description still adds real value: partial payments are allowed and stackable, amounts above the balance due or future dates are refused, and the invoice transitions Active to Paid on full payment. It also discloses the confirmation-prompt default and that it can be disabled per tool. It does not say whether a recorded payment can later be edited or reversed, which matters for a destructive mutation.

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 action and method list, with constraints following in a sensible order. It wastes some space by stating the Active-to-Paid transition twice ("paid in full moves to Paid" and "Once paid in full the invoice moves from Active to Paid"), which could be a single clause.

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 four-parameter mutation with no output schema, the description covers validation rules, partial-payment behavior, state transitions and confirmation semantics, which is most of what an agent needs. The remaining gap is that it never indicates what a successful call yields (e.g., a payment identifier or the updated invoice balance), which an agent may need for follow-up steps.

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 100%, so amount, method, paid_on and invoice_id are all documented in the schema and the baseline is 3. The description does add one constraint beyond the schema: an amount above the balance due is refused, and a future paid_on is rejected, neither of which the schema expresses. That is a modest but genuine semantic addition over an already-complete schema.

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 and resource ("Record a ... payment on an invoice") and enumerates the accepted methods, which map directly to the method enum. It also distinguishes itself from the in-app Joist Payments flow by scoping itself to payments "received outside Joist Payments," so an agent can tell what this does versus the automated path.

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 pre-call workflow ("Check get_invoice first so the same check is not entered twice") and names the get_invoice sibling explicitly, plus the condition that this is for payments outside Joist Payments. It stops short of naming a distinct alternative tool to use instead when the payment did come through Joist Payments, so the routing guidance is clear but not exhaustive.

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