Skip to main content
Glama

Search teas.co.uk

find_products
Read-onlyIdempotent

Use this when someone wants to find, browse or choose tea, hot chocolate or other drinks to buy from teas.co.uk, a UK online tea shop. Not for general tea knowledge. query is the customer's own words; leave it out to browse by filters alone. Every filter given applies at once. max_price is per pack in pounds and max_price_per_cup_pence is per cup in pence. Results come best match first unless sort says otherwise. Out of stock products stay hidden unless include_out_of_stock is true. There is no paging: limit caps the list and total says how many matched, so narrow the filters to see others. If nothing matches, time_of_day, strength, format and with_milk are dropped in that order and note says which; kind, caffeine, labels, iced and price limits are never dropped. Prices are live and include VAT. Next: get_product for one product, compare_products to compare, add_to_basket to buy.

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_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
icedNoSuits iced tea or cold brew.
kindNoType of drink.
sortNoOrder of results: best_match (the default), cheapest_per_cup, price_low_to_high, price_high_to_low or strongest.
limitNoHow many products to return (default 6).
queryNoWhat the customer wants in their own words, for example "strong breakfast tea", "Yorkshire Gold" or "something for bedtime". Leave out to browse with filters only.
veganNoOnly products labelled vegan.
formatNoHow it comes: tea_bags, loose_leaf, instant, pods_or_capsules, sachets, powder or ready_to_drink.
organicNoOnly organic products.
caffeineNoCaffeine: caffeinated, decaf (caffeine taken out), caffeine_free (none to begin with, such as rooibos and most herbal teas) or low_or_none (decaf or caffeine free).
strengthNoHow strong the cup is: light, medium or strong.
fairtradeNoOnly Fairtrade products.
max_priceNoHighest pack price in pounds.
with_milkNoOnly products that suit milk.
time_of_dayNoWhen it suits best: morning, afternoon, evening or bedtime.
include_out_of_stockNoAlso include products that are out of stock (they are left out by default).
max_price_per_cup_penceNoHighest price per cup in pence.

Output Schema

NameRequiredDescriptionDefault
noteNoPresent when filters were left out: tell the customer, in your own words.
totalYesHow many products matched before the limit.
filtersNoThe filters that were applied.
relaxedNoPresent when no product matched every filter: the filters left out to find these.
productsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / format / description
      Previous value: -"How it comes: tea_bags, loose_leaf, instant, pods_or_capsules, sachets, ground or whole_beans (coffee), powder, coffee_bags or ready_to_drink."New value: +"How it comes: tea_bags, loose_leaf, instant, pods_or_capsules, sachets, powder or ready_to_drink."
    • changedInput schema / properties / format / enum
      Previous value: -[
      -  "tea_bags",
      -  "loose_leaf",
      -  "instant",
      -  "pods_or_capsules",
      -  "sachets",
      -  "ground",
      -  "whole_beans",
      -  "powder",
      -  "coffee_bags",
      -  "ready_to_drink"
      -]New value: +[
      +  "tea_bags",
      +  "loose_leaf",
      +  "instant",
      +  "pods_or_capsules",
      +  "sachets",
      +  "powder",
      +  "ready_to_drink"
      +]
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "black",
      -  "green",
      -  "white",
      -  "oolong",
      -  "herbal",
      -  "fruit",
      -  "rooibos",
      -  "chai",
      -  "matcha",
      -  "earl_grey",
      -  "coffee",
      -  "hot_chocolate"
      -]New value: +[
      +  "black",
      +  "green",
      +  "white",
      +  "oolong",
      +  "herbal",
      +  "fruit",
      +  "rooibos",
      +  "chai",
      +  "matcha",
      +  "earl_grey",
      +  "hot_chocolate"
      +]
  2. Changed9 schema fields changed
    • addedInput schema / properties / caffeine / description
      Added value: +"Caffeine: caffeinated, decaf (caffeine taken out), caffeine_free (none to begin with, such as rooibos and most herbal teas) or low_or_none (decaf or caffeine free)."
    • addedInput schema / properties / fairtrade / description
      Added value: +"Only Fairtrade products."
    • addedInput schema / properties / format / description
      Added value: +"How it comes: tea_bags, loose_leaf, instant, pods_or_capsules, sachets, ground or whole_beans (coffee), powder, coffee_bags or ready_to_drink."
    • addedInput schema / properties / include_out_of_stock / description
      Added value: +"Also include products that are out of stock (they are left out by default)."
    • addedInput schema / properties / organic / description
      Added value: +"Only organic products."
    • addedInput schema / properties / sort / description
      Added value: +"Order of results: best_match (the default), cheapest_per_cup, price_low_to_high, price_high_to_low or strongest."
    • addedInput schema / properties / strength / description
      Added value: +"How strong the cup is: light, medium or strong."
    • addedInput schema / properties / time_of_day / description
      Added value: +"When it suits best: morning, afternoon, evening or bedtime."
    • addedInput schema / properties / vegan / description
      Added value: +"Only products labelled vegan."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the supplied readOnly/idempotent annotations, the description discloses non-obvious behavior: filters combine conjunctively, out-of-stock items are hidden by default, there is no paging so limit caps and total counts, and on empty results a specific ordered set of filters (time_of_day, strength, format, with_milk) is relaxed while kind, caffeine, labels, iced and price limits are never dropped, with a note field reporting which. It also warns that prices are live and VAT-inclusive, which matters for any agent quoting a figure.

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 when-to-use sentence and the exclusion, then moves to behavior and finally to next steps, with no filler sentences. It is dense and slightly run-on in the middle (fallback-order and no-paging rules packed together), but for a 16-parameter tool essentially every clause carries decision-relevant information.

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?

For a 16-parameter, zero-required search tool with an output schema present, the description covers everything an agent needs to call it correctly: default sort, default limit, default exclusion of out-of-stock items, absence of paging, the degradation order on empty results, and where to go next. Return-value details are rightly deferred 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; the description earns above that by disambiguating the two price parameters (per pack in pounds vs per cup in pence), clarifying that query is free-text customer wording and may be omitted for filter-only browsing, and stating that all supplied filters apply simultaneously. It stops short of discussing the boolean label filters (vegan, organic, fairtrade), which the schema already handles plainly.

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 description states a specific verb-and-resource pair ('find, browse or choose tea, hot chocolate or other drinks to buy') and bounds the scope to teas.co.uk, a UK online tea shop. It explicitly excludes the adjacent-but-different case ('Not for general tea knowledge'), so an agent can separate it from informational siblings without opening a 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?

It gives a concrete triggering condition ('when someone wants to find, browse or choose... to buy'), an explicit exclusion ('Not for general tea knowledge'), and names three follow-on siblings (get_product, compare_products, add_to_basket) with the condition that selects each. Very little is left to inference.

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