Skip to main content
Glama

Save a Request

save_request
Idempotent

Save a new free, private, non-binding Request for delivery in the US or Israel, when the person asks you to or says yes to what you showed them. Ask once, together, for what’s missing: how many, when they need it and their postal code (ZIP in the US). “A chair” means one; for a plural or a vague wish, never assume a number. If they skip something, save without it. A model can come later. Use it for a future purchase the person will buy later, with no rush or to wait for a better or group price: physical goods, not services, digital goods or anything needed within days. With several items, ask “If only some items come through, do you still want those?” once; the person may skip it. If they state a maximum for everything together, record it as the Request-wide price_limit with includes_delivery_and_tax true. A limit without “in total” or “each” is unclear. Ask once which they meant, or in a background task leave it out. Record no as all_items_required true, with the items they need marked required; record yes or a skip as false, the default, where each item settles on its own deal. Works well: a specific, comparable item (brand and model or accepted alternatives) that can wait days to weeks, about $50 to $100+, shipped within the buyer’s country. Works poorly: urgent or perishable goods, custom items, services, regulated or restricted goods, very cheap items. If possible_duplicate_of lists the same thing, ask the person which to keep. Relay save_confirmation.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "request": "<request>"
    },
    "name": "save_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestYesThe Request: the person’s words, items they want, where and when.
request_keyNoOptional. The same key repeats a change safely; one is derived when left out.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / request / properties / items / items / required
      Previous value: -[
      -  "description",
      -  "quantity"
      -]New value: +[
      +  "description"
      +]
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so much of the write/idempotency profile is structured data. The description adds non-obvious behavior beyond that: the Request is "free, private, non-binding", partial saves are allowed, duplicates must be resolved with the person ("If possible_duplicate_of lists the same thing, ask the person which to keep"), and save_confirmation must be relayed. It does not discuss auth requirements or rate limits, so it stops short of a 5.

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

Conciseness3/5

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

It is front-loaded with the purpose and primary trigger, which is good, but the body is a dense single paragraph that mixes usage policy, conversational scripting and parameter mapping with no structure. Several sentences are hard to parse in isolation ("Record no as all_items_required true, with the items they need marked required") and the ambiguity/recovery instructions repeat the "ask once" pattern several times.

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?

For a deeply nested schema with an output schema and full annotations, the description covers the decisions an agent actually has to make: when to save, what to collect, what to omit, how to handle ambiguity and duplicates, and how to relay confirmation. Filling in the conversational policy is the right use of the description slot, and return-shape detail is correctly delegated to the output schema.

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, but the description goes further by mapping natural language onto specific parameter values: a total-order maximum becomes the Request-wide price_limit with includes_delivery_and_tax true, and "no" maps to all_items_required true with the needed items marked required, while yes-or-skip maps to false. It also guards quantity ("'A chair' means one; never assume a number"). It does not touch need_by or delivery semantics, hence a 4 rather than 5.

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 first clause names a specific verb and resource and its scope: "Save a new free, private, non-binding Request for delivery in the US or Israel." It immediately distinguishes what is created (a Request, not an order) and constrains geography, so an agent can tell it apart from get_request/update_request siblings 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 when-to-use trigger ("when the person asks you to or says yes to what you showed them"), explicit when-not-to-use list ("Works poorly: urgent or perishable goods, custom items, services, regulated or restricted goods, very cheap items"), and explicit routing for adjacent cases (order-wide cap belongs on the Request price_limit, not the item's). Missing data handling ("If they skip something, save without it. A model can come later") is also stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources