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

Discloses real behavioral traits beyond the annotations: the possible outcomes (resume a pending charge, complete verified fulfilment, or return a 3DS/Stripe.js action requirement), the ownership check against Stripe, and the anti-retry safety rule. One ambiguity: it calls the pending charge 'idempotent' while annotations declare idempotentHint=false, which could mislead an agent into blind retries, though the phrase describes the charge rather than the call.

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 verb and scope, then outcomes, then the negative constraint and the alternative. Three dense sentences with no filler or repeated annotation content.

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?

With no output schema and a single parameter, the description carries the burden well by enumerating the three possible terminal states and warning against retry. Minor gaps remain around what the agent should do with a returned 3DS action and any machine-registration/auth prerequisites, but nothing critical for correct invocation 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?

Schema coverage is 100% and the sole parameter already documents its own provenance in nearly identical wording, so the description adds little beyond the schema. The added value is only the reminder that the ID must come from a stripe_off_session purchase specifically, which is baseline-adequate for a one-param tool.

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 ('Reconcile') and resource ('saved-card purchase') and pins the input's provenance to a sibling tool ('order_id returned from purchase with payment_method=stripe_off_session'). It also distinguishes itself from get_order and from sync_card_authorization by describing what it does that they don't (PaymentIntent ownership/status check).

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 explicit preconditions (an order_id from a stripe_off_session purchase), explicit prohibitions ('Do not retry with a new order or bypass bank authentication'), and names the alternative for a different need ('use get_order to read ordinary delivery status'). The when/when-not routing is fully specified.

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