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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavioral context: an indeterminate-return failure mode for incomplete facts, a legal disclaimer, per-call pricing with a free tier, and three payment routes. Minor gaps remain (what 'auditable' entails in the response, whether failed/indeterminate calls are billed).

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 its constraints, then legal and payment housekeeping. Every sentence carries operational weight (allowed values, indeterminate behavior, cost, payment route); nothing is padding given the paid-call model.

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?

An output schema exists, so return values needn't be explained, and the payment/nondeterminism behavior is well covered. But 'facts' is an open nested object (additionalProperties: true) with no key guidance, and the description never points to get_rule_pack as the source of the required credit-specific fact keys — a notable gap for a tool whose failure mode is 'missing facts'.

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 0%, so the description must compensate. It does well for two of four params — 'credit' gets an explicit allowed-value list and 'facts' gets content requirements plus failure semantics — but 'request_id' is never mentioned and 'payment_ref' is only alluded to obliquely via the escrow funding path.

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 ('Calculate an auditable tax-credit scenario') and enumerates the exact credit universe (45Q, 45V, 45Y, 48E, 45X), which is information the schema does not carry since 'credit' is an untyped string with no enum. It is clearly distinguishable from the verification sibling verify_tax_credit_result.

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?

It specifies an input precondition ('facts must contain the explicit credit-specific eligibility facts; missing facts return indeterminate'), which is real usage guidance. But it never says when to reach for this versus get_rule_pack (to learn which facts are required) or verify_tax_credit_result (to check a result), so the sibling routing is left implicit.

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