Skip to main content
Glama
Device Specs MCP Server

Device Specs MCP Server

by GranTurismo

Search phones by hardware filters

search_phones
Read-onlyIdempotent

Filter the smartphone catalog by hardware criteria such as RAM, battery, refresh rate, chipset, or features using property keys and operators; supports paging and compact output.

Instructions

Find smartphones matching hardware criteria using the API's filter language: keys are '[_]' and values are strings, numbers or booleans. Operators: (none)=equals, _gt, _gte, _lt, _lte, _contains, _in (comma list), _between ('min,max'), _has. Common properties: manufacturer, model, chipset, ram (GB), storage (GB), battery (mAh), refresh_rate (Hz), displaysize (inches), panel_type, brightness (nits), charging (W), wireless_charging, weight (g), ip_rating, nfc, headphone_jack, card_slot, stereo_speakers, infrared, price_usd, announcedate, android. Example: {"manufacturer":"Samsung","ram_gte":12,"refresh_rate_gte":120,"battery_gte":5000}. All filters are ANDed. Call list_filter_properties for the complete list of properties and aliases. Results come back in catalog order (roughly newest first within a brand).

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": {
      "filters": "<filters>"
    },
    "name": "search_phones"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of phones to return (1-200, default 25).
offsetNoNumber of phones to skip, for paging through large result sets.
compactNotrue (default) returns a short projection of ~20 key fields per phone to save tokens; false returns the full raw API JSON.
filtersYesMap of filter key to value, e.g. {"chipset_contains":"Snapdragon 8 Gen 3","ram_gte":12,"headphone_jack":true}. Unknown keys are ignored by the API.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: filters are ANDed together, results return in catalog order (roughly newest first within a brand), and unknown keys are silently ignored — the last point is important because it means typos fail silently rather than erroring.

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?

It is front-loaded with the most important fact (the filter-key grammar) and every sentence carries information. The long inline property enumeration is dense but earns its place as a quick-reference; it could have been deferred entirely to list_filter_properties, which slightly hurts tightness.

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 4-parameter read-only search with a nested filter object and no output schema, this covers the essentials: how to build filters, how filters combine, ordering of results, and a pointer to the full property catalog. The only gap is that return shape and paging behavior are left to the schema's compact/offset descriptions rather than explained here.

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%, so a 3 would be the floor, but the description goes far beyond the schema by documenting the entire filter key grammar ('<property>[_<operator>]'), all nine operators, accepted value types, the common property vocabulary, and a concrete example object. The schema only says filters is a map of key to value; the description is what makes the parameter actually usable.

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 ('Find smartphones matching hardware criteria') and immediately defines the filter language, so the agent knows this is the general hardware-search tool. It does not explicitly contrast itself with the simpler siblings like list_phones_by_manufacturer or list_phones_by_chipset, so sibling differentiation is only partial.

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

Usage Guidelines3/5

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

It gives one useful routing instruction — 'Call list_filter_properties for the complete list of properties and aliases' — which tells the agent how to discover valid keys. However, there is no guidance on when to prefer this over the manufacturer/chipset convenience tools, nor any note on paging strategy despite offset/limit existing.

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