Skip to main content
Glama

Remode - Fashion Finder, New & Pre-loved

Start a Hunt for a fashion product in Remode

watch_item
Destructive

Create or refresh an account-linked Hunt for a specific fashion product URL. Call this only when the shopper clearly wants Remode to keep watching this item over time: keep watching or looking, watch it for a lower price or second-hand options, alert or notify me, tell me or let me know when, start a Hunt, or an ask to hunt it for them that also asks what Remode will watch for, for example 'Hunt this for me and tell me what you will watch for, my size is M, I live in Switzerland': pass url, size exactly as the shopper wrote it, and region as a country code. A hypothetical or informational question about Hunts ('what would a Hunt watch for?', 'how does a Hunt work?') is not a request to start one: answer it without a write and offer to start a Hunt. A request for results now ('hunt down cheaper options for this link right now', 'find me', 'is it cheaper') is a one-time comparison: use check_price and never create a Hunt. If it is unclear whether the shopper wants ongoing watching, use check_price and offer to start a Hunt. After the call, say only Colette's confirmation at the start of the returned text, and its one question if that confirmation has one, then stop. Do not add small talk, do not say please wait, and do not say Carrie will look or that a second-hand search is running. Carrie speaks only in a later update when a verified second-hand piece exists. The rest of the returned text is the mandate, not a script to read out. A new hunt request needs no earlier read; read existing Hunts first only when the shopper refers to a Hunt they already have, because this can replace an existing Hunt's terms. Use update_watch for criteria edits; do not re-create an existing Hunt unless the shopper explicitly requests a replacement and all desired terms can be represented. Percent-off targets cannot be set here. Exact item only: the Hunt never widens to similar items. Optional terms: same-currency max_price, condition, and size supported by a retailer variant record. Explicit in_stock=false can enable restock monitoring; never infer stock. Persisted state and ongoing monitoring are inside Remode: this creates a Remode Hunt, not a reminder or scheduled task in the assistant, and Remode keeps checking until the Hunt is stopped. The call returns as soon as the Hunt is queued; it does not scan. Say only Colette's confirmation and its one question if present, then stop. Do not add small talk, do not say please wait, and do not say Carrie will look or that a second-hand search is running. Carrie speaks only in a later update when a verified second-hand piece exists.

Input Schema

NameRequiredDescriptionDefault
urlYesRetailer product URL from a Remode result.
sizeNoThe shopper's size as the store labels it. Remode applies it only when it can read the store's own per-size stock; otherwise the Hunt continues for the exact item without a size and the result says so.
colorNoThe exact item's colour as the store names it. When the store sells the item in several colours, a size is applied only together with one of the store's own colour labels; on a single-colour product page the size is applied without a colour.
priceNoVisible current price including currency when known.
titleNo
regionNoShopping country code, such as US, CH, DE, or GB.
in_stockNo
conditionNoSay-when condition for this exact item: new (new listings only; second-hand listings never count), pre_owned (second hand), or any (both). Use instead of preferences.
image_urlNo
max_priceNoPrice finish line for this exact item: alert only at or below this price, in this currency. Must be the item's own currency; Remode never converts currencies. Works with condition new, pre_owned or any: a second-hand (pre_owned) watch can carry this absolute price ceiling. A percent-off target is not settable here.
preferencesNoWhat Remode should look for. Defaults to lower price and second hand.
use_saved_sizeNoUse the shopper's saved usual size for this category as the size, when size is not given. Read-only; never changes the saved sizes.

Output Schema

NameRequiredDescriptionDefault
okYes
sizeNo
regionYes
watchedYes
watch_idYes
preferencesYes
price_targetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / max_price / description
      Previous value: -"Price finish line for this exact item: alert only at or below this price, in this currency. Must be the item's own currency; Remode never converts currencies. Requires condition new or any."New value: +"Price finish line for this exact item: alert only at or below this price, in this currency. Must be the item's own currency; Remode never converts currencies. Works with condition new, pre_owned or any: a second-hand (pre_owned) watch can carry this absolute price ceiling. A percent-off target is not settable here."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover the safety profile (readOnly=false, destructive=true, idempotent=false, openWorld=true). The description adds substantial context beyond that: the call returns as soon as the Hunt is queued and does not scan, monitoring is persisted inside Remode and continues until stopped, it is not an assistant reminder or scheduled task, this can replace an existing Hunt's terms, percent-off targets are unrepresentable, and the Hunt never widens to similar items.

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?

Purpose and routing rules are correctly front-loaded, but the final block is duplicated almost verbatim: 'Do not add small talk, do not say please wait, do not say Carrie will look... Carrie speaks only in a later update when a verified second-hand piece exists' appears twice, along with a repeated 'Say only Colette's confirmation... then stop.' This is padding, not conciseness.

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?

An output schema exists, so return values need no explanation, yet the description still tells the agent how to handle the returned text (read only Colette's confirmation and its single question; the mandate is not a script). Combined with the routing, persistence, and mutation caveats, nothing needed to call this 12-parameter tool correctly is missing.

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 75%, below the threshold where the schema alone suffices. The description adds real semantics: size must be passed 'exactly as the shopper wrote it', region as a country code, max_price must be the item's own currency (never converted), condition as a say-when filter, and in_stock=false must be explicit and never inferred. It does not add much for url, title, image_url, or preferences beyond the schema.

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?

Opens with a specific verb+resource+scope: 'Create or refresh an account-linked Hunt for a specific fashion product URL.' It immediately differentiates itself from siblings by naming check_price for one-time comparisons and update_watch for criteria edits, so an agent can route without opening any other 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 triggers are enumerated verbatim ('keep watching', 'alert me', 'start a Hunt'), and when-not-to-use is equally explicit: hypothetical questions get no write, results-now requests go to check_price and never create a Hunt, ambiguity defaults to check_price. It also states the pre-read condition (read existing Hunts first only when the shopper refers to an existing Hunt) and the update_watch alternative.

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