Paraíso

request_reservation

Request a table at a restaurant. THE RESTAURANT IS NOT NOTIFIED YET: the request is held and a confirmation email is sent to the address you provide, and only when that person clicks the link does the restaurant receive it. Tell the user to check their inbox — the link expires in 24 hours. Use a real address belonging to the person you are acting for; the confirmation link is deliberately not returned to you. This is a request, not a confirmed booking: the restaurant confirms out of band.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Name the table is under.
`email`	Yes	The guest's own email — the confirmation link is sent here.
`phone`	No	Optional phone number for the restaurant to reach the guest.
`message`	No	Optional note (occasion, dietary needs, seating preference).
`partySize`	Yes	Number of people (1–30).
`place_slug`	Yes	Restaurant place slug from search_places.
`requestedAt`	Yes	Desired date and time as an ISO instant. Must be in the future.

TDQS

A4.3/5.0

Behavior5/5

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

With no annotations, the description fully describes the tool's behavior: the request is held, a confirmation email is sent, the restaurant is notified only after the user clicks, the link expires in 24 hours, and the confirmation link is not returned to the agent. This is comprehensive and honest.

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 with about 4 sentences, each adding critical information. It front-loads the purpose and then delivers behavioral caveats efficiently. Could be slightly improved with clearer separation of points.

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?

Given the multi-step workflow (email confirmation, expiry, out-of-band restaurant confirmation) and no output schema, the description covers essential post-invocation actions and user instructions. It omits error handling details but is otherwise complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds context on using a real email for the guest and that phone and message are optional, but does not introduce new parameter details 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?

The description clearly states 'Request a table at a restaurant' and distinguishes it from a confirmed booking by highlighting that the restaurant is not notified until the user clicks a confirmation link. This differentiates it from sibling tools like 'create_booking'.

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 provides clear usage context: use a real email, inform the user to check inbox, and notes the 24-hour link expiry. It implicitly advises against treating this as a confirmed booking, though it doesn't explicitly list alternative tools for when a confirmed booking is needed.

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

All Paraíso 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

A4/5.0

Disambiguation5/5

Each tool targets a distinct domain (booking, store checkout, events, restaurant, etc.) with clear descriptions. No two tools have overlapping purposes; even similar actions like create_booking, create_checkout, and reserve_event_tickets are differentiated by their specific contexts.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with underscores (e.g., get_availability, list_blog_posts, reserve_event_tickets). There is no mixing of conventions like camelCase, and verbs are predictable (get, list, create, search, submit, etc.).

Tool Count4/5

With 28 tools, the count is slightly on the high side but justified by the broad scope covering a neighborhood directory with multiple features (places, events, movies, menus, bookings, forms, etc.). Each tool serves a clear purpose, though a few could be consolidated.

Completeness4/5

The tool surface is comprehensive for the server's purpose, covering search, details, bookings, events, movies, menus, blogs, FAQs, forms, and more. Minor gaps exist (e.g., no tool to cancel bookings or update reviews), but core workflows are well-covered.

Resources

Need Help?