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

Annotations already declare idempotentHint=true and readOnlyHint=false, so the description goes beyond that by detailing the exact payment flow: if a Stripe Shared Payment Token is present, it charges and delivers instantly; otherwise it escalates and redirects. It also notes that included reports complete without charge and that meta['idempotency-key'] is required. This is rich behavioral context beyond the structured hints.

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 a single paragraph but packs several essential details: the main action, two payment paths, the report exception, and the idempotency-key requirement. It is front-loaded with the purpose and then explains conditions. It is appropriately sized for the complexity, though slightly dense; a bullet list might improve readability, but it remains efficient.

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 3 parameters, nested objects, and an output schema (not shown but present), the description covers all necessary behavior for correct invocation: the payment decision logic, the escalation path, the report exception, and the required metadata fields. Nothing an agent needs to call this tool correctly is missing.

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?

While schema coverage is 100% with parameter descriptions, the description adds critical semantic value: it specifies that the checkout parameter carries the payment credential and precisely defines the trigger (handler_id 'stripe' and credential.token starting with 'spt_'). It also emphasizes the mandatory idempotency-key in meta, which the schema only marks as optional. This goes well beyond the schema's generic text.

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 states a specific verb and resource ('Completa una sesión de checkout UCP') and clearly differentiates from siblings like create_checkout, update_checkout, cancel_checkout, and get_checkout by focusing on the finalization step. It also explains the two payment outcomes, making the tool's purpose unmistakable.

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 explains the conditions under which the tool charges instantly vs escalates, and mentions the report case. It does not explicitly say 'use this instead of X', but the context is clear that this is the checkout finalization tool, and the payment logic gives a strong sense of when to invoke it. It could name the alternative for non-finalized sessions but that is implied by the siblings.

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