Get showtimes for a specific movie at cinemas in this neighborhood, for a given date. Returns each cinema with session times, format (e.g. "Laser", "3D"), and language (Dublado/Legendado). Requires movies_enabled on this site.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Date in YYYY-MM-DD format. Defaults to today (BRT). | |
| movie_slug | Yes | Movie slug from list_movies (e.g. "o-corvo-1016084"). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the return structure (cinema, session times, format, language) and a prerequisite (movies_enabled). The verb 'Get' strongly implies a read-only operation, and it does not hide side effects. It lacks error-case handling but is reasonably transparent for a simple query tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, with purpose first, then return details, then a prerequisite. Each clause adds value, with no redundant information. It is well-structured and concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read tool with two parameters and no output schema, the description sufficiently covers purpose, return format, and a prerequisite. It is slightly incomplete in explaining how to determine 'movies_enabled' or the meaning of 'this neighborhood,' but given the tool's simplicity, it is adequate. Not a full 5 due to these minor gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers both parameters with clear descriptions (date format, movie_slug from list_movies). The description adds minimal extra meaning beyond mapping 'given date' and 'specific movie' to the parameters. With 100% schema coverage, the baseline of 3 applies, and the description does not enhance beyond that.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb 'Get' and resource 'showtimes for a specific movie at cinemas in this neighborhood, for a given date.' It distinguishes itself from siblings by focusing on movie showtimes and specifying return fields (session times, format, language). This leaves no ambiguity about the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by requiring a specific movie and date, and notes the prerequisite 'Requires movies_enabled on this site.' It does not explicitly mention alternatives or exclusions, such as using list_movies to find the movie_slug, but the context is clear. It provides a clear usage context without exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource or action: booking services, restaurant reservations, event tickets, and RSVPs are all clearly separated by domain and described with explicit use cases. Similarly, search_places, search_dishes, and get_restaurant_menus cover different granularities of place/menu lookup. The descriptions include guidance on when to use each tool, eliminating ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., list_*, get_*, create_*, search_*). While a few verbs like 'request' and 'rsvp' differ, they accurately reflect the action's semantics and do not break the overall consistency. The naming makes the tool's purpose predictable from its name.
At 28 tools, this is a large set, but it serves a broad multi-domain directory (places, events, movies, store, bookings, content, etc.). Each tool covers a distinct feature or resource, and there are no redundant tools. The count is at the upper boundary but appropriate for the server's comprehensive scope.
The tool surface covers the full lifecycle for the directory's main domains: search/discover places, view details, menus, reviews, book services, reserve/RSVP events, browse movies/showtimes, list products, access content (blog, guides, FAQs), submit forms, and check loyalty. There are no obvious dead ends or missing operations for the stated purpose. The inclusion of pairing tools like list_forms→submit_form and get_availability→create_booking shows deliberate workflow completeness.