Skip to main content
Glama

WIPE Around

Find local businesses in Israel

search_businesses
Read-onlyIdempotent

Search WIPE Around's map of Israel's local businesses (beauty and wellness, health, trades, food, shops, classes…). Write what is wanted in plain Hebrew: the town, the trade, a budget and a time are read from the words, e.g. "קוסמטיקאית ברעננה", "חשמלאי בחולון", "טיפול פנים בחיפה עד 400 השבוע". In English the town, a budget and a time are not read from the words (a business's name and some trade words are), so give the town as city, the trade as kind, and a budget or a time as max or when. A budget (עד 400) or a time (היום or עכשיו for today; מחר, השבוע or בשבוע הקרוב for the week) read only from the words orders the results instead of filtering them. A business known to meet it is lifted (see the order): a published price for it at or under the budget, a free time then in a WIPE booking calendar. One that has not said (no published price for it, or no online booking) stays in the results, and its unconfirmed names what to ask it. One known not to meet it is left out, unless the words give its own name: a higher price, or online booking with no free time then in a WIPE booking calendar. Given as max or when, a budget or a time filters instead. Results come best first, each with its page, phone, WhatsApp, prices and why it fits, and, when it takes bookings through a WIPE site, a booking link and the first free time in its WIPE calendar, if any. Results are ordered by how well they match the words and the trade, how near they are to a location when one is given (for businesses added from the towns around a town asked for, to that town's centre), availability, how complete the page is, reviews and who runs the page. The words can lift a business above that order: one whose own name they give comes first, even outside the trade, the town, the budget or the time asked for; then one that says yes to what they ask of the place (a language spoken there, coming to the home) comes before one that has not; then one known to meet a budget or a time typed in them comes before one that has not said. Availability: any online booking counts a little, and free time in a WIPE booking calendar in the seven days from today counts more, most when its first free time is today or tomorrow and it has free time on five or more of those days. Reviews: only Around's own, written through the link of a booking made on WIPE; reviews from other sites never count. Who runs the page: a page its owner verified counts most, then one its owner manages from a WIPE site, then a page from open data. So a business that books online, more so through a WIPE calendar with free time, and a page run from a WIPE site or verified, rank higher.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoWhat is wanted, in plain Hebrew (the town, the trade, a budget and a time are read from it); in English, a business's name or a trade.
latNoWith lng, a point to measure from: how near a business is counts in the order, and a town in city or in the words no longer filters. The search reads the businesses within about 25 km of it, and any whose name carries the words wherever they are. The point is used only when both lat and lng are given and it lies in or near Israel.
lngNoWith lat.
maxNoHighest price in shekels, to filter.
cityNoA town's slug or Hebrew name, to filter.
kindNoA trade's slug (cosmetics, hair, nails, body, electricians…), to filter.
whenNoOnly businesses with a free time in a WIPE booking calendar: later today (today) or in the seven days from today (week), Israel time. Free times are read only from the booking calendars of businesses that take bookings through their WIPE site, so a business without one never matches, even one that takes bookings by phone, on WhatsApp or through another booking site. The one exception is a business whose own name the words in q give: it comes first whatever its free times. When the search finds no business at all, the filter is let go: the results are the same search without it, and query.relaxed includes "when".
limitNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations already establish a safe read-only, idempotent, open-world operation, and the description goes well beyond them: it discloses the ranking factors, the ~25 km radius behavior, availability semantics, the review provenance rule, and the relaxation behavior (a no-result 'when' filter is dropped and query.relaxed includes it). This is unusually rich behavioral context.

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 first sentence is well front-loaded, but the body is a very long, rambling paragraph with nested parentheticals and repeated restatements of the same ranking/filtering rules. The information is valuable but poorly condensed and hard to scan.

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 complex ranked search tool with no output schema, it explains what results contain (page, phone, WhatsApp, prices, booking link, first free time), how they are ordered, and edge cases like relaxation. It is close to complete, though the density makes it hard to verify nothing important was lost.

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 already high (88%), so baseline would be 3, but the description adds real meaning beyond the schema – notably the distinction that Hebrew words trigger parsing/reordering whereas max/when are filters, and that lat/lng only apply when both are given and lie in/near Israel. Some redundancy with the schema remains.

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?

States a specific verb and resource ('Search WIPE Around's map of Israel's local businesses') with the covered categories listed, so the agent knows it is a discovery/search tool. It does not explicitly name or contrast with the sibling get_business, but the verb 'search' versus a detail lookup is reasonably inferable.

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?

Gives concrete when/how guidance: write in plain Hebrew to have town/trade/budget/time parsed from words, or use city/kind/max/when in English, plus the key rule that budget/time in words reorder while max/when filter. It lacks an explicit statement of when to prefer this over the sibling get_business.

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