Skip to main content
Glama
chrischall

myhotlunchbox-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

mhlb_create_order

Place a school lunch order into the cart from the order form model with quantities set. Confirm the preview before approval; this does not pay—checkout handles payment.

Instructions

Place a lunch order into the cart. Call mhlb_get_order_form first and send that model back with quantities set. This adds to the cart — it does not pay; use mhlb_checkout for that. Asks the user to confirm first: a confirmation prompt where the client supports one; otherwise the first call returns a preview and a confirmToken, and only a repeat call with that token proceeds (see MCP_CONFIRM_MODE). NOTE: this write is UNVERIFIED — its request shape was derived from the web app’s compiled API client but has not been exercised against a live account. Inspect the confirmation preview before approving it.

Input Schema

NameRequiredDescriptionDefault
orderYesThe order model — the `data` object returned by mhlb_get_order_form / mhlb_get_order — with quantities and options edited.
confirmTokenNoONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 "confirmation-required" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.7
    • changedInput schema / properties / order / description
      Previous value: -"The order model, as returned by mhlb_get_order_form / mhlb_get_order, with quantities and options edited."New value: +"The order model — the `data` object returned by mhlb_get_order_form / mhlb_get_order — with quantities and options edited."
  2. Changed2 schema fields changedv1.2.1
    • removedInput schema / properties / confirm
      Removed value: -{
-  "description": "Must be true to proceed. Without this, the tool returns a preview.",
-  "type": "boolean"
-}
    • addedInput schema / properties / confirmToken
      Added value: +{
+  "description": "ONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 \"confirmation-required\" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.",
+  "type": "string"
+}
  3. Changed1 schema field changedv1.0.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  4. First observedv0.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description goes well beyond that: it discloses the elicitation vs. two-step confirmation protocol, the preview/confirmToken flow, the MCP_CONFIRM_MODE dependency, and — critically — that the write is UNVERIFIED and derived from a compiled client, advising inspection of the preview. That is exactly the kind of behavioral context annotations cannot provide.

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 action and the required prior call, then the payment boundary, then confirmation mechanics, then the verification caveat. Every sentence carries distinct information, though the confirmation/token sentence is dense enough that it could be split for faster scanning.

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?

No output schema exists, yet the description explains the response shapes that matter — the confirmation prompt, or a preview plus confirmToken — and the precondition call needed to construct the nested `order` object. For a nested-object, open-world write tool, nothing essential is left unspecified.

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 100%, so the baseline is 3. The description earns above baseline by tying the `order` parameter to its source ('the model returned by mhlb_get_order_form, with quantities and options set') and by adding strict invocation rules for confirmToken — never on first call, never invented, never reused, ignored under elicitation — which reinforce the schema text rather than merely repeating it.

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 a lunch order into the cart') and immediately scopes it against siblings: it adds to the cart rather than paying, and names mhlb_checkout for payment. An agent can distinguish this from mhlb_get_order_form, mhlb_checkout, and mhlb_update_order without opening any schema.

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?

Explicit prerequisites ('Call mhlb_get_order_form first and send that model back with quantities set'), explicit boundaries ('it does not pay; use mhlb_checkout for that'), and explicit when-to-confirm behavior including the token fallback. This is a full routing decision, not an implication.

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

Deploy Server

Other Tools