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

Annotations already indicate mutation (readOnlyHint=false) and non-destructive behavior. The description adds crucial context: it charges the buyer, requires buyer approval in Link, and specifies that the token must be requested for the exact amount scoped to a specific Stripe profile. It also explains that on error the booking remains open until the hold expires. This is substantial behavioral disclosure beyond what annotations provide. However, it does not explicitly mention idempotency (though idempotentHint=true) or explain that the tool may be safely retried, so a 4 is appropriate.

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 dense but front-loaded: it opens with the primary action and immediately gives the key prerequisite. Each subsequent clause adds necessary context (token request, approval, charging, success/failure handling). While it is longer than a typical description, every sentence serves a purpose, and no redundant or filler content is present.

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?

Given the tool's complexity (payment, external approval, error states) and that an output schema exists, the description is complete. It covers the success outcome (booking paid, ticket_url), failure handling (payment_url, hold expiry), and the required token properties. An agent can call this tool correctly and know what to expect without missing critical information.

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 schema covers 67% of parameters (booking_uuid lacks a description). The description compensates by explaining booking_uuid as the target of the remaining balance, and for shared_payment_token it adds that it must be requested for exactly amount_to_pay_cents in EUR scoped to a specific Stripe profile. This adds meaning beyond the schema's bare 'spt_… token' description. The locale parameter is adequately described in the schema, so the description's lack of mention is acceptable.

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 action: 'Pays the remaining balance of a booking' with a Shared Payment Token. It specifies the sequencing (after set_contact and any pass/gift card) which distinguishes it from sibling payment-related tools like redeem_gift_card and redeem_pass. The verb and resource are explicit and 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?

The description provides explicit usage conditions: it must be called after set_contact and after any pass or gift card, and only after the buyer confirms the purchase. It also gives handling guidance for success (booking paid, ticket_url) and failure (give payment_url to human buyer). This effectively tells an agent when to use this tool versus other steps, leaving no ambiguity about sequencing.

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