Skip to main content
Glama

find_alternatives

Where else can my agent buy this? Give a blocking domain and/or a category (electronics, gift-cards, groceries, apparel, hardware, books, travel, crypto-hardware, other, or a product word like headphones). Product words resolve to a finer sub (headphones -> audio). Returns in-map stores an agent can reach that sell that product family, ranked by checkout reached, major retailer, main product line, agent access, BTC grade, checkout ease, each with an evidence URL, plus turned_away stores with reasons. Index only; never crawls.

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": "find_alternatives"
  }
}

Input Schema

NameRequiredDescriptionDefault
payNo
subNoproduct family
zipNo5-digit US ZIP: adds landed cost per store
guestNotrue (or 1) = drop stores known to REQUIRE an account; a store whose guest status is unknown is kept (guest: null) and ranked after confirmed-guest stores. confirmed = strict: only stores confirmed to allow guest checkout. false (or 0) = no guest filter. Items carry guest (true|false|null) and co
limitNo
domainNo
taxpreNowith zip: only stores observed to show shipping and tax before payment
categoryNocoarse category or product word (headphones, laptop, gift card...)
include_blockedNoalso list stores whose checkout is blocked (bot wall or refusal); they rank last. Default false.
include_indirectNowith pay=btc/lightning: also list stores where bitcoin works only through a third-party processor or gift card (labelled btc_route indirect). Default: native acceptance only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / guest / description
      Previous value: -"exclude stores known to require an account"New value: +"true (or 1) = drop stores known to REQUIRE an account; a store whose guest status is unknown is kept (guest: null) and ranked after confirmed-guest stores. confirmed = strict: only stores confirmed to allow guest checkout. false (or 0) = no guest filter. Items carry guest (true|false|null) and co"
    • addedInput schema / properties / guest / enum
      Added value: +[
      +  true,
      +  false,
      +  "1",
      +  "0",
      +  "confirmed"
      +]
    • changedInput schema / properties / guest / type
      Previous value: -"boolean"New value: +[
      +  "boolean",
      +  "string"
      +]
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does substantial work: it discloses the ranking factors (checkout reached, major retailer, product line, agent access, BTC grade, checkout ease), that each result carries an evidence URL, that turned_away stores are included with reasons, and that results come from an index rather than live crawling. Remaining gaps are rate limits, auth needs, and result freshness, which is why it is not 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.

Conciseness4/5

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

The definition is front-loaded with the core question and the required inputs before the return-value sentence, which is the right ordering. It is dense rather than padded, though the long enumeration of ranking factors makes the final sentence a run-on that could be tightened.

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 10-parameter, zero-annotation tool with no output schema, the description supplies what an agent needs: the triggering scenario, the input modes, the ranking logic, the shape of results including evidence URLs and turned_away entries, and the index-only data limitation. Only secondary operational details (defaults, rate limits, error behavior) are absent.

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?

At 70% schema coverage the baseline is a 3, and the description does add real meaning for two parameters: 'blocking domain' and the category/product-word resolution (headphones -> audio). However, pay, zip, guest, limit, include_blocked and taxpre are explained only in the schema or not at all, so the description does not fully compensate for the coverage gap.

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

Purpose4/5

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

The description states a specific verb and resource: it returns alternative in-map stores where an agent can buy a product family, given a blocking domain and/or category. The opening question frames the use case crisply, and the scope ('Index only; never crawls') is explicit. It does not name a sibling such as search_merchants or find_agent_native, so the boundary with those tools must be inferred.

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?

Usage context is clear: 'Where else can my agent buy this?' plus 'Give a blocking domain and/or a category' tells the agent this is the fallback when a specific store blocks it. It also explains how product words resolve to finer subs. It stops short of explicitly naming when to prefer search_merchants or find_agent_native instead, so there are no stated exclusions.

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.