Skip to main content
Glama

iDevice Buyer's Guide

Find the device that fits

find_best_device
Read-onlyIdempotent

A short ranked list of on-sale products in one category for a shopper: optionally the phone platform they use, a budget, and up to three priorities from the uses iDevice's Guides assign (for example sleep, running, battery-life, photos-video). Each product comes with its verdict (buy_now or wait), its fit with the phone given, today's retailer price, a one-line reason and its sources, and the place its Guide gives a named priority. In the list: a verdict of Buy now or Wait, and Works or Works with limits with the phone given. Order: the verdict, then the fit answer, then where the product's Guide places a named priority among the uses it lists, then price. A priority outside the Guides' uses is refused and the uses are listed. The same list as the decision card on idevice.com. For earbuds, when iDevice's earbuds recommendation is published, the order is that recommendation's instead: quality and fit from independent reviewers' findings, card by card (all-around, music and sound, workouts, noise cancellation, calls, value), with the buy-or-wait verdict shown beside each product, where it does not move the product; the answer adds a recommendation block naming each card's pick, strong choices or why there is none, and reads at most two priorities from calls, sound, anc, workouts and comfort. iDevice's own pick answers first, in every category it covers (earbuds, headphones, watches, fitness trackers, glasses, headsets and phones): the product it names for your question, then the alternatives it names, each with its verdict, fit, price and sources, and a best_answer block with the reviews behind the pick. Your phone and budget decide which products fit you, not which is better. Priorities are the uses the pick covers (for example sleep, running, battery life, calls); a use outside them is refused and the uses are listed.

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": {
      "category": "<category>"
    },
    "name": "find_best_device"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many products, 1 to 5, default 3
categoryYesThe kind of product
budget_usdNoA price ceiling in US dollars
prioritiesNoUp to three uses, e.g. ['sleep','battery-life']. A use iDevice's Guides do not assign is refused, with the list.
owned_platformNoThe phone platform the shopper uses

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / category / enum
      Previous value: -[
      -  "glasses",
      -  "rings",
      -  "watches",
      -  "earbuds",
      -  "phones",
      -  "headsets",
      -  "fitness trackers"
      -]New value: +[
      +  "glasses",
      +  "rings",
      +  "watches",
      +  "earbuds",
      +  "phones",
      +  "headsets",
      +  "fitness trackers",
      +  "headphones"
      +]
  2. Added

TDQS

B3.2/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add genuinely useful behavioral detail — and it does: out-of-Guide priorities are refused with the valid uses listed, phone and budget affect fit rather than ranking, and the earbuds path overrides the default ordering. Some behaviors are stated twice and none of it is organized, but the substance an agent needs to predict the response is present.

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

Conciseness2/5

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

The description is a multi-clause wall of run-on sentences that packs output ordering, an earbuds special case, a cross-category best-pick path and a best_answer block into one paragraph. The priority-refusal rule is stated twice, and the reader has to reverse-engineer the structure. Only the first sentence is properly front-loaded.

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 and five parameters, the description carries the full burden of explaining return values, and it does so thoroughly — verdict, fit, ordering, price, sources, and the best_answer/recommendation blocks. What is missing is a compact statement of where this tool sits relative to siblings and which path (default vs earbuds vs own-pick) applies when, but the content coverage itself is high.

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, and the description earns a bump by explaining the semantics behind the parameters: priorities must be uses the Guides actually assign (with refusal plus enumeration otherwise), and owned_platform/budget_usd gate fit rather than quality. It also names concrete example priorities (sleep, running, battery-life, photos-video), which clarifies the otherwise free-form array of strings beyond what the schema says.

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

Purpose3/5

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

The opening line does establish a concrete deliverable — a short ranked list of on-sale products in one category, with verdicts and fit — so the resource and output shape are identifiable. But the purpose is buried under a dense stream of ordering rules, earbud exceptions and block names, and nothing distinguishes it from likely-overlapping siblings such as find_products, get_best_for, pick_between or should_i_buy. An agent can guess what it does, but only after parsing the whole block.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, and no alternative is named. The only orienting statement is 'The same list as the decision card on idevice.com', which is framing rather than routing advice. The agent is left to infer that this is the fit-based shopping recommendation tool rather than the comparison or review tools.

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.