Skip to main content
Glama

Uk Food Hygiene

by io.github.pipeworx-io

Uk Food Hygiene Search

uk_food_hygiene_search
Read-onlyIdempotent

Search UK restaurant food hygiene ratings from the Food Standards Agency FHRS — answers "is this restaurant clean", "is this takeaway safe to eat at", "food hygiene rating of X". Search by business name and/or address (a town, street, or postcode works), or by latitude/longitude + radius_miles for hygiene ratings near a point. Filter by business_type (restaurant, takeaway, pub, hotel, supermarket, mobile caterer...) and min_rating (1-5). Returns rating (0-5 in England/Wales/NI; Scotland uses "Pass"/"Improvement Required" under FHIS), inspection date, address, and inspection sub-scores. Example: uk_food_hygiene_search({ name: "Nandos", address: "Leeds" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoBusiness name to search, e.g. "Nandos", "Golden Dragon"
limitNoMax results to return, 1-30 (default 10)
addressNoAny part of the address — town, street, or postcode, e.g. "Leeds", "Baker Street", "SW1A 1AA"
latitudeNoLatitude for geo search (use with longitude)
longitudeNoLongitude for geo search (use with latitude)
min_ratingNoMinimum FHRS rating 1-5 (5 = best). Filters to numerically-rated FHRS establishments, so Scottish FHIS results drop out
radius_milesNoGeo search radius in miles (default 2, max 30). Only used with latitude/longitude
business_typeNoOptional type filter, e.g. "restaurant", "takeaway", "pub", "hotel", "supermarket", "school", "mobile caterer"

TDQS

A4.6/5.0
Behavior5/5

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

The description adds significant context beyond annotations: explains Scotland uses FHIS with different ratings ('Pass'/'Improvement Required'), that min_rating drops Scottish results, and what is returned (rating, date, address, sub-scores). No contradiction with annotations (readOnly, openWorld, idempotent).

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?

The description is efficient and front-loaded with purpose. It is slightly lengthy due to examples and details, but every sentence adds value. Could be more concise, but structure is clear.

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?

Given 8 parameters, no output schema, and no enums, the description is very complete. It explains return contents, geographic differences, filter implications, and provides examples. It adequately compensates for missing 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 covers all 8 parameters (100% coverage), baseline 3. Description adds value with context: explains address can be town/street/postcode, min_rating range and effect on Scottish results, radius defaults and limits, and provides usage examples. This goes beyond 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?

The description clearly states it searches UK restaurant food hygiene ratings from FHRS, provides specific examples, and distinguishes from sibling tools (e.g., uk_food_hygiene_details). It includes verb 'Search' and specifies resources and what it answers.

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?

The description gives clear context on when to use: for finding hygiene ratings by name/address or geo. It includes examples and filter options. However, it does not explicitly state when not to use it or mention alternatives beyond implied sibling.

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

All Uk Food Hygiene toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Several tools blur together: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all answer questions over the same data, and five polymarket_* tools overlap on edge detection and arbitrage. Descriptions help somewhat, but the boundaries are subtle and the server name 'Uk Food Hygiene' adds a layer of confusion.

Naming Consistency3/5

All names are lowercase snake_case, but conventions vary widely: brand-style names (ask_pipeworx, pipeworx_feedback), noun phrases (entity_profile, recent_changes), verb_noun pairs (list_subscriptions, validate_claim), and bare verbs (recall, forget). It is readable but does not follow one predictable pattern.

Tool Count1/5

A server named 'Uk Food Hygiene' has 33 tools, of which only two (uk_food_hygiene_search, uk_food_hygiene_details) relate to food hygiene. The rest are a grab-bag of Pipeworx platform utilities, prediction-market tools, memory helpers, and subscription features — an extreme mismatch between count and stated scope.

Completeness2/5

The two food hygiene tools cover search and detail lookup, which handles the core use case, but the broader tool surface has notable gaps: citation URIs are returned but no fetch/read tool exists, and the unrelated domains (prediction markets, company research, AI visibility) are deep in some places and absent in others. The overall surface feels like an incoherent collection rather than a complete domain toolkit.

Resources