Filipe Coffee

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

A4.6/5.0

Behavior4/5

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

With no annotations, the description fully discloses the key behaviors: the request is held, a confirmation email is sent with a 24-hour expiry, and the restaurant is notified only after confirmation. It also states that the confirmation link is not returned to the caller. This is comprehensive, though it omits details like error cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (4 sentences) and front-loaded with the primary purpose. Every sentence provides essential information without redundancy. It is well-structured for quick comprehension.

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 lack of output schema, the description adequately explains the outcome: the request is held and a confirmation email is sent. It covers the asynchronous nature and expiry. It could mention what happens on failure (e.g., invalid email), but overall it is sufficient for an agent to understand the tool's behavior.

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?

The input schema covers all 7 parameters with descriptions (100% coverage). The description adds value by reinforcing that 'email' must be the guest's own and that 'requestedAt' must be a future ISO instant. It also advises to use a real address, going 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 the purpose: 'Request a table at a restaurant.' It uses a specific verb ('Request') and resource ('table'), and distinguishes itself from siblings like 'create_booking' by emphasizing it is a request, not a confirmed booking.

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?

The description provides explicit guidance: the restaurant is not notified until the guest confirms via email, the link expires in 24 hours, and the user should check their inbox. It also warns to use a real address and that this is a request, not a confirmed booking, which helps avoid misuse.

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

All Filipe Coffee 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 resource or action (e.g., bookings, events, places, menus, forms), with detailed descriptions that clearly differentiate even similar operations like create_booking vs. reserve_event_tickets. No two tools overlap in purpose.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using lowercase and underscores (e.g., create_booking, get_availability, list_events). Verbs are semantically appropriate (create, get, list, search, submit) and predictable.

Tool Count4/5

28 tools is slightly above the typical 3-15 range, but the breadth of the neighborhood directory domain justifies each tool. The count feels dense but not excessive, with no redundant tools.

Completeness5/5

The tool set covers the full lifecycle of a neighborhood directory: place search, restaurant menus, events, movie showtimes, booking, reviews, blog, guides, offers, loyalty, forms, and profiles. Obvious gaps like review creation are absent but likely out of scope.

Resources

Need Help?