Skip to main content
Glama

confirm_order

Place and pay for a Yandex Lavka order after the user confirms the previewed total. Charges the card only if the cart matches the preview.

Instructions

Place the order and CHARGE the card. Irreversible — real money.

Call ONLY after checkout_preview was run and the user explicitly said yes to the previewed total. Pass that exact total as confirmed_total. The order is refused unless: a preview was run recently, confirmed_total matches it, and — critically — the live cart still matches the previewed cart at submit time (same version and total). If anything drifted, nothing is charged and you must preview + confirm again.

Returns the order id and payment_status. "wait_user_action" means the bank requires 3-D Secure — give the user redirect_url to finish paying. cancel_order cancels.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
confirmed_totalYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.5

TDQS

A4.8/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full behavioral burden and it does so richly: 'Irreversible — real money', refusal conditions (recent preview, matching confirmed_total, cart version/total match at submit), the drift behaviour ('nothing is charged'), and the 3-D Secure wait_user_action flow with redirect_url. These are exactly the traits an agent needs before invoking 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the verb and the risk warning, then ordered preconditions, then the return semantics. The 3-D Secure sentence and the trailing 'cancel_order cancels' are slightly terse but each earns its place; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A money-moving mutation with no annotations and an output schema present. The description covers the risk, the precondition logic, the drift/refusal behaviour, and the wait_user_action return path, while the output schema handles the return shape. Nothing an agent needs to call this safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate for the single parameter, and it does: it explains what confirmed_total means ('that exact total'), where it comes from (the previewed total), and the validation rule (must match the preview). The only gap is that it doesn't give the numeric format, but that is minor for a number field.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Place the order') plus the consequential action ('CHARGE the card'), and explicitly distinguishes itself from checkout_preview and cancel_order by naming both. Nothing about the purpose is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use ('Call ONLY after checkout_preview was run and the user explicitly said yes') and when-not-to (order is refused unless preconditions hold), and names the sibling to run before it. This is the strongest possible form of routing guidance.

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