retry_paymentRetry an unpaid hosted payment attempt after signed-in browser approval.
| Name | Required | Description | Default |
|---|---|---|---|
| attempt_id | Yes | ||
| confirmation_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly=false and idempotentHint=false, so the agent knows this mutates state and is not safe to repeat. The description adds a state precondition ('unpaid', 'after signed-in browser approval') that is genuinely useful. However, it does not disclose what happens on success (a charge is triggered) or that a non-idempotent payment retry has financial consequences if called repeatedly. No contradiction with annotations, but the behavioral disclosure is shallow for a money-moving operation.
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?
A single ten-word sentence with the verb and resource front-loaded and the precondition at the end. Every word earns its place; there is no repetition of the name or title and no filler.
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?
The output schema covers return values, but this is a payment-affecting, non-idempotent operation with 0% parameter coverage and no sibling routing. An agent lacks the information to know where confirmation_id comes from, when to call this versus resume_payment, and what side effects (a charge) will occur. For a high-stakes financial call, the definition is under-specified.
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 carry the parameter explanation burden, and it does not. 'unpaid hosted payment attempt' hints at attempt_id and 'signed-in browser approval' hints at confirmation_id, but neither parameter is named, and the source/format of confirmation_id (e.g., where the agent obtains it after approval) is unexplained. This is insufficient for an agent to confidently populate a required and an optional input.
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 uses a specific verb ('Retry') with a clear resource ('unpaid hosted payment attempt') and adds a precondition ('after signed-in browser approval'). This is clearly not a tautology and is more specific than 'Retry Payment'. However, it does not explicitly differentiate itself from its nearest sibling, resume_payment, so it stops short of full sibling distinction.
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?
There is no when-to-use or when-not-to-use guidance, and no alternatives are named. With 28 siblings including resume_payment, cancel_payment_attempt, and start_checkout, the agent gets no routing help. The phrase 'after signed-in browser approval' implies a context, but it never tells the agent which sibling to choose instead under other conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly separated by resource and action (cart, orders, tickets, picks, payments), so an agent can generally select the right one. The only notable ambiguity is resume_payment vs retry_payment, which both describe acting on an unpaid hosted payment attempt with nearly identical wording.
All 29 tools follow a consistent snake_case verb_noun (or verb_preposition_noun) pattern with standard verbs like get, list, create, close, remove, and set. There are no mixed conventions or vague generic names.
At 29 tools this is a heavy surface, but the broad e-commerce scope (catalog, cart, checkout, payment, orders, support, rewards) justifies most of them. A few payment-attempt tools could be consolidated, so it sits at the overbuilt rather than absurdly bloated end.
The set covers the main customer journey from browsing/searching sarees through cart, checkout, payment status, orders, and post-purchase support. Minor gaps exist—for example, no explicit apply_coupon/redeem_points tool or standalone catalogue listing—but agents can work around them with validate_coupon, checkout summary, and search.