agentcard

buy

Destructive

Shop and check out, in natural language, across the merchants the user has linked (DoorDash, etc.). Pass the whole ask as request — e.g. "order a caesar salad from Zuni on DoorDash" — and this tool runs the shopping flow for you. It is CONVERSATIONAL: this tool RETURNS a conversation_id; pass that SAME conversation_id back on every follow-up (your reply to a question, "add a coke", "yes, check out") so it continues the SAME order. Omit it (or set new_order=true) only to start a fresh order. It will ask for the delivery address and have you confirm the cart and total. CHECKOUT (which charges a one-time card) happens ONLY after the user explicitly confirms in a later message — relay the confirmation through request ("yes, place the order") on the SAME conversation_id. RELAY REPLIES VERBATIM: when the user answers a question from this tool ("yes", "the 16 oz one", "use my other card"), pass their reply through request as-is on the same conversation_id — do NOT rewrite it into a fresh full order command; a rewritten command reads as a NEW ask and the confirmation never lands. NEVER use new_order (or drop the conversation_id) to recover from an error or a refused checkout — that discards the cart and any pending confirmation. Stay on the same conversation_id and follow the error's instruction instead; new_order is ONLY for the user starting an unrelated order. If it hands out a merchant login link (hosted connect), just reply on the SAME conversation_id once the user finishes (e.g. "done — I logged in") and it verifies the link itself. Logins started here have no pending_id, so the buy_connect / buy_connect_status pair does not apply to them. Call get_instructions FIRST for the current usage guide before your first buy.

Input Schema

TableJSON Schema

Name	Required	Description
`request`	Yes	The natural-language ask or follow-up, e.g. "order a caesar salad from Zuni on DoorDash", "deliver to 123 Main St", or "yes, place the order".
`new_order`	No	Start a fresh shopping conversation instead of continuing the current one. Use when beginning an unrelated order (ignores any conversation_id).
`conversation_id`	No	The conversation_id returned by a previous buy call. Pass it to continue the SAME order (keeps the cart + confirmation). Omit to start a new order.

Output Schema

TableJSON Schema

Name	Required	Description
`status`	No	Discriminator for the outcome. 'assistant_turn' when the buy loop replied; 'conversation_start_failed' or 'request_failed' on errors.
`message`	Yes	The assistant's conversational turn (it may ask for the delivery address, show the cart + total, confirm, or report a placed order), or an error explanation.
`messages`	No	The same turn split into ordered messages for multi-bubble surfaces (each narration segment, then the final reply/confirmation). `message` is the same content consolidated; clients that show one bubble should use `message` and ignore this.
`conversation_id`	No	The conversation id to thread back as conversation_id on the next buy call to continue the SAME order. Present on a successful assistant turn.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedJul 28, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Discloses critical behavioral traits beyond annotations: the tool returns a conversation_id that must be reused, checkout 'charges a one-time card' only after explicit user confirmation, replies must be relayed verbatim, and using new_order/timeout 'discards the cart and any pending confirmation.' This is exactly the kind of context an agent needs to avoid dangerous mistakes.

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?

The description is long, but every paragraph addresses a distinct critical aspect: conversational flow, checkout confirmation, error recovery, login links, and prerequisite guidance. It is front-loaded with purpose and uses capitalization/emphasis effectively. Dense but justified for a complex, potentially destructive tool.

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?

Given the tool's high complexity and the presence of an output schema, the description fully covers the flow, prerequisites, alternative tools, safety rules, and error handling. An agent has everything needed to select and invoke this tool correctly.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds significant semantics: request can be a follow-up or full ask with concrete examples, conversation_id must be 'the SAME conversation_id' for continuity, and new_order 'ignores any conversation_id' and is only for unrelated orders. The prose meaningfully clarifies all three parameters beyond the schema.

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?

The description explicitly states the tool 'Shops and checks out, in natural language, across the merchants the user has linked' and 'runs the shopping flow for you.' This clearly distinguishes it from siblings like buy_connect or buy_list_merchants, which handle narrower aspects of the shopping lifecycle.

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?

Usage guidance is explicit and actionable: 'Call get_instructions FIRST for the current usage guide before your first buy.' It also explains when buy_connect/buy_connect_status do not apply ('Logins started here have no pending_id') and details when new_order is appropriate versus when it must never be used for error recovery.

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

All agentcard tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, especially in areas like card management and shopping. However, the KYC flow has multiple overlapping tools (start_kyc, get_kyc_status, check_kyc_document, submit_kyc_document, submit_kyc_fields) that could confuse an agent despite detailed descriptions.

Naming Consistency4/5

Tool names consistently use snake_case with a verb_noun pattern (e.g., add_funds, create_card, list_cards). A few exceptions like surprise_me and whoami break the pattern but are still intuitive overall.

Tool Count3/5

50 tools is on the high side for a single server, but the broad domain (cards, shopping, KYC, support, settings) partially justifies it. Some tools could be merged (e.g., KYC flow tools) without losing clarity.

Completeness4/5

The tool surface covers core workflows: CRUD for cards, transactions, KYC, support, shopping, and account management. Minor gaps exist (e.g., no update_card general, no cancel order in shopping), but overall the set is comprehensive for the stated purpose.

Resources

Need Help?