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

Annotations only flag write/destructive/open-world, but the description discloses a rate limit on remind (once per day, max 3), that cancel voids the payer's link, that refund returns money in full or partial cents, that regenerate_link invalidates the old link and returns a new payUrl, the idempotency-key retry contract, third-party email side effects, and a PII handling prohibition. This is well beyond what the annotations convey.

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 product context followed by action semantics and then labeled sections (Prerequisite, Canonicality, Idempotency, Confirmation boundary). It is long and repeats generic retry/canonicality boilerplate that applies broadly to Corply tools, but nearly every sentence conveys actionable constraint.

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 7-parameter, destructive, no-output-schema tool, the description supplies effects, safety constraints, confirmation requirements, prerequisites, and a pointer to returned actual_tool_output/payUrl. The main residual gap is return-shape detail on the newly generated link and the undocumented companyId/_corply_context parameters.

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?

With only 29% schema description coverage, the description compensates for the key parameters: it explains the semantics of each action enum value, the refundAmountCents integer-cents/full-refund behavior, and the stable idempotencyKey retry rule. companyId and the _corply_context object remain unexplained in both description and schema, which keeps this from a 5.

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+resource ('Act on one exact request') and enumerates all four actions (remind, cancel, refund, regenerate_link) with the effect of each, so an agent can distinguish this from list_payment_requests, request_payment, or await_payment without opening any schema. The opening sentence also frames the domain (Corply Pay) so the tool's scope is unambiguous.

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 per-action applicability ('cancel an open request', 'refund a paid request', 'regenerate_link kills the old link') and a prerequisite (authenticated active company access) plus a hard confirmation gate before calling. It does not name explicit alternatives among the many payment siblings (e.g., request_payment vs manage_payment_request), leaving some routing inference to the agent.

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