Skip to main content
Glama

QQuickpick

search_titles

Find movies and/or TV shows that are genuinely available on a subscription streaming service in a specific country, filtered by score, genre, runtime, age rating, release year, country of origin, required cast members, notable people's own watch history, review tone, and similarity to a title the user already knows. All given filters combine with AND logic (except where noted). Use this instead of guessing streaming availability from general knowledge, which is frequently wrong or outdated -- catalogs change constantly and vary by country. Also use this tool for completely open-ended requests with no stated criteria at all, e.g. "suggest something to watch" or "I don't know what I want to watch" -- call it with just the country and no other filters to get QQuickPick's currently popular streamable picks, rather than answering from general knowledge alone. Movie results also carry a "facts" object (or null when unknown): Best Picture winner/nominee, Oscars won ("at least" -- the source is not exhaustive, so never state it as an exact count), festival top prizes, the work it is based on, and its franchise with all films in order. Use the awards / based_on_existing_work / franchise filters (movies only) to answer questions like "Oscar winners based on a novel I can stream tonight" or "all films of a franchise available to me". Use similar_to for "something like X" requests instead of guessing similar titles from general knowledge. Use origin_countries for requests like "an Asian film" or "a French series" -- do not guess specific titles from general knowledge for this. Each result includes a site_url (QQuickPick detail page) and, where available, a watch_link with required attribution -- include these links when presenting results to the user, not just the raw facts. The response also carries a top-level available_filters hint listing filters on this tool that were not used in this call -- consider offering ONE of them as a natural follow-up question, not all of them, and only when it fits the conversation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo
sortNo"hot" = most popular first, "new" = newest releases first.hot
typeNoSearch movies, TV shows, or both.all
genreNoGenre name, e.g. "Action", "Comedy", "Documentary".
actorsNoRequire all of these actors to appear together in the cast (AND logic) -- use this for "a film starring both X and Y". If, and only if, that combination has no streamable results at all, the response automatically falls back to titles matching any one of them individually, each tagged with a matched_actors field -- mention that distinction to the user rather than presenting it as if they all appeared together.
awardsNoMovies only. Multiple values are OR logic -- keep films with at least one (not all) of these honours: best_picture_winner, best_picture_nominee (includes winners), oscar_winner (won any Oscar), festival_top_prize (Palme d'Or, Golden Bear, Golden Lion or the Cannes Grand Prix), bafta_best_film (BAFTA for Best Film), golden_globe_best_picture (Golden Globe for Best Motion Picture, drama or musical/comedy). The underlying data is not exhaustive (it knows roughly 40% of BAFTA/Golden Globe winners), so a missing honour does not prove a film did not win it. Sorted by score.
countryYesISO 3166-1 alpha-2 country code (e.g. "NL", "US", "GB") for the streaming region -- determines which subscriptions and age ratings apply. This cannot be detected automatically: an MCP server only sees its host infrastructure, never the end user's real location. If the user's country has not been stated in this conversation, ASK the user before calling this tool -- do not guess or default to one, since a wrong country returns streaming availability that does not apply to them.
year_toNo
franchiseNoMovies only. Return the films of one franchise / film series in release order, e.g. "The Lord of the Rings", "Dune", "Harry Potter". Only films that are streamable in the given country are returned.
max_scoreNo
min_scoreNoMinimum TMDB score, 0-10.
year_fromNo
similar_toNoFind titles similar to this one, e.g. "Inception" or "The Office", ranked by QQuickPick's own similarity signal rather than a guess from general knowledge. Resolves the given title first (use the type filter to disambiguate a movie vs TV show sharing a name); if type is "all", both a similar movie and a similar TV show are looked up independently. Combines with the other filters as normal (AND logic).
watched_byNoOnly titles watched/reviewed by at least one of these notable people on QQuickPick (directors, critics, actors curating their own watch history), e.g. ["Martin Scorsese"]. OR logic across multiple names. Unknown names are ignored with a warning -- this is a small curated list of profiles, not a general "who has seen this" lookup.
review_vibeNoFilter by the tone of the title's reviews rather than a numeric score: funny, unique-take (an unusual angle), harsh (critical), or heartfelt. Multiple values are OR logic -- a title matches if it has at least one review with any of the given vibes, not all of them (e.g. ["funny","heartfelt"] returns titles that are either, not both at once -- a serious drama with one heartfelt review can appear here). Experimental -- runs on a curated sample of reviews, not the full catalog, so absence of a result does not mean no title has that vibe.
kid_friendlyNoIf true, only keep titles rated for general/family audiences in the target country (resolved to that country's own mildest local rating, e.g. G/U/AL). A convenient shortcut for max_age_rating when the exact local rating string is unknown -- do not set both; if both are given max_age_rating wins and kid_friendly is ignored with a warning. Not applied together with awards, based_on_existing_work, franchise, watched_by, review_vibe or similar_to (ignored there too, with a warning).
exclude_genreNoGenre name to exclude, e.g. "Horror" for "anything but horror". Opposite of genre.
max_age_ratingNoMaximum age/content rating in the target country's own local rating system, e.g. "12", "PG-13", "16".
origin_countriesNoISO 3166-1 alpha-2 country/countries the title was originally produced in (e.g. "KR", "JP", "IN") -- NOT the streaming region. Multiple values are OR logic, e.g. ["KR","JP","IN"] for "an Asian film". Use this instead of guessing specific titles from general knowledge when the user asks for films/shows from a region rather than a specific country.
critics_vs_viewersNoMovies only. Keep only films where professional critics and ordinary viewers agree, where critics like the film more than viewers do, or where viewers like it more than critics. Only the verdict is available, never the underlying scores; films without enough critic data are left out.
streaming_servicesNoRequire the title to be on at least one of these subscription streaming services, e.g. ["Netflix", "Disney Plus"]. Omit to allow any subscription service in that country.
max_runtime_minutesNo
min_runtime_minutesNoMinimum runtime in minutes (movies) or minimum episode runtime (TV).
based_on_existing_workNoMovies only. If true, keep only films adapted from an existing work (novel, comic, earlier film, ...).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses AND/OR logic, automatic fallback behavior for actors, non-exhaustive awards data, experimental review_vibe sampling, kid_friendly interaction caveats, the inability to auto-detect country, and the available_filters follow-up hint.

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 long but earned: it covers 24 parameters and many cross-parameter interactions. It front-loads the core purpose and the most important anti-guessing guidance, then flows into parameter-specific rules. Minor structural improvement would be bullets or shorter paragraphs, but each sentence adds value.

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?

For a complex 24-parameter tool with no output schema and no annotations, the description is remarkably complete. It covers parameter semantics, edge cases, interaction warnings, fallback behavior, data quality caveats, and even response elements like site_url, watch_link, and available_filters. An agent has enough context to invoke it correctly in varied conversational scenarios.

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

Parameters5/5

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

Schema description coverage is 79%, and the description still adds significant meaning beyond the schema: country must be asked not defaulted, actors fall back with matched_actors, awards values are OR with data caveats, kid_friendly conflicts are resolved with warnings, and origin_countries is explicitly about production origin, not streaming region. This goes well beyond the baseline.

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 opens with a specific verb and resource: find movies and/or TV shows genuinely available on subscription streaming in a specific country. It clearly distinguishes the tool from general-knowledge guessing and from the sibling get_title_details by framing this as the search/exploration tool.

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 gives explicit when-to-use guidance: use for streaming availability rather than guessing, use for open-ended requests, use similar_to for 'something like X', and use origin_countries for regional requests. It also states when NOT to guess and instructs the agent to ask the user for the country, which is critical operational guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources