Skip to main content
Glama

Checkout (stops before paying)

blinkit_checkout

Prepares a cart with items for payment and returns the bill plus a live browser link, so the user reviews the delivery address and pays; payment is never completed by the tool.

Instructions

Readies the cart for payment and stops: it never pays. Returns the bill and a live link to the browser where the person reviews the address and pays themselves. Needs a logged-in account with items in the cart.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "blinkit_checkout"
  }
}

Input Schema

NameRequiredDescriptionDefault
addressNoLabel or text of the saved address to deliver to, if it should change

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does the most important job: it declares the tool does not take payment, which is the key safety property for a commerce write operation. It also discloses the return payload (bill plus a live browser link) and auth/cart preconditions. It does not say whether the cart is locked, modified, or expires after the call, which matters for a step that mutates state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Three short sentences, no filler, and the most consequential fact ('it never pays') is front-loaded before the return-value and prerequisite details. Every clause conveys new information.

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

Completeness4/5

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

With no output schema, the description usefully explains what comes back (bill and browser link) and sets preconditions for the call. Remaining gaps are failure modes — empty cart, missing login, invalid address — and post-call cart state, which the agent may need for recovery.

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

Parameters3/5

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

The single optional 'address' parameter is already fully documented in the schema (100% coverage), so the baseline applies. The description never mentions the address argument, leaving the agent to learn from the schema that it controls the delivery address label.

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 action ('readies the cart for payment') and, critically, its boundary ('and stops: it never pays'), which separates it from an actual payment step and from read-only siblings like blinkit_view_cart. The title's parenthetical reinforces rather than repeats the description.

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

Usage Guidelines4/5

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

Prerequisites are explicit ('needs a logged-in account with items in the cart') and the human hand-off is spelled out ('the person reviews the address and pays themselves'), which tells the agent this is the last automated step. It stops short of naming an alternative tool or stating when the tool should be re-invoked after address changes, so it lacks explicit exclusions.

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