Vila Mariana

search_places

Search for places (restaurants, cafes, shops, etc.) in this neighborhood. The q match is accent-insensitive and typo-tolerant ("acai" finds "Açaí", "restaurnt" finds "Restaurante"), ranked by relevance. Compose filters for multi-condition queries: category, neighborhood, open_now (true = open at this exact moment), and attributes (amenity slugs, ALL must match). Each result includes a precomputed open_now boolean, an attributes array (amenity slugs), a delivery array of curated delivery-app deep-links (ifood, rappi, 99food, uber-eats — each { platform, url }), rating, and structured hours (Google Maps periods: day 0=Sun–6=Sat, time "HHMM"). Common amenity slugs: wifi, outdoor-seating, wheelchair, dog-friendly, delivery, takeaway, reservations, live-music, vegan, gluten-free (availability varies per place).

Input Schema

TableJSON Schema

Name	Required	Description
`q`	No	Free-text term matched against place name and address — accent-insensitive and typo-tolerant.
`limit`	No	Max results to return (default 20, max 100).
`category`	No	Filter by category label (e.g. "Café"). Case-insensitive substring match.
`open_now`	No	When true, return only places open at the current local time (computed server-side from their opening hours).
`attributes`	No	Amenity slugs a place must ALL have, e.g. ["wifi","outdoor-seating"]. Common slugs: wifi, outdoor-seating, wheelchair, dog-friendly, delivery, takeaway, reservations, live-music, vegan, gluten-free.
`neighborhood`	No	Filter by neighborhood name. Case-insensitive substring match.

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries full burden. It transparently discloses: accent-insensitive and typo-tolerant matching, ranking by relevance, server-side open_now computation, ALL-matched attributes, and result fields including precomputed booleans and structured hours. It omits error handling and rate limits but is highly informative for a search tool.

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 concise yet thorough, covering purpose, matching, filters, and result fields in a logical order. It front-loads the primary use and then detail. At ~300 words, it avoids verbosity while packing necessary information. Minor redundancy could be trimmed, but overall efficient.

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?

With no output schema, the description adequately explains key result fields (open_now, attributes, delivery, rating, hours). It covers all six input parameters with behavioral context. Missing details like pagination, default limit, or error responses are tolerable for a search tool but could be added for full completeness.

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%, providing a baseline of 3. The description adds significant value: it explains `q` matching effects (typo-tolerance), `open_now` as current local time, `attributes` as slugs requiring ALL match, and lists common amenity slugs with examples. This exceeds schema descriptions and aids correct usage.

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 the tool searches for places (restaurants, cafes, shops) in a neighborhood, using specific verbs and examples. It implicitly distinguishes from siblings like 'search_dishes' by focusing on places and offering multi-condition filters with unique features (typo-tolerance, amenity slugs).

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?

The description explains how to compose filters ('Compose filters for multi-condition queries') and mentions matching behavior, but does not explicitly guide when to use this tool vs alternatives (e.g., 'get_place' for a single place, 'search_dishes' for dishes). No when-not or exclusionary advice is given.

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

All Vila Mariana tools Inspect

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

A4.1/5.0

Disambiguation5/5

Each tool targets a distinct action and resource: booking appointments, restaurant reservations, event tickets, searches, etc. No two tools have overlapping purposes; even similar actions like create_booking and request_reservation are for different domains (appointments vs. restaurant tables).

Naming Consistency5/5

All tools follow a consistent verb_noun pattern using lowercase and underscores (e.g., get_availability, list_events, create_booking). There is no mixing of styles like camelCase or inconsistent verbs.

Tool Count4/5

28 tools is above the typical well-scoped range but each tool serves a clear purpose within the comprehensive neighborhood directory domain. The count feels justified, though slightly heavy.

Completeness4/5

The tool set covers most major features of a neighborhood directory: places, events, booking, restaurant menus, reviews, forms, etc. Minor gaps exist, such as no create_review or update operations, but core workflows are complete.

Resources

Need Help?