Skip to main content
Glama
Sign In
Crawlora MCP

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

rottentomatoes_movie_reviews

Rotten Tomatoes movie reviews. Returns Rotten Tomatoes movie reviews, newest first. All four type values return the full review feed in one request: each review carries a stable id, ISO created_at/updated_at timestamps, the critic…

Instructions

Rotten Tomatoes movie reviews. Returns Rotten Tomatoes movie reviews, newest first. All four type values return the full review feed in one request: each review carries a stable id, ISO created_at/updated_at timestamps, the critic identity and the original article URL, and the list is pageable limit reviews at a time: pass data.page_info.end_cursor back as after for the next page and keep limit the same while paging. data.transport is feed_api for that path. A title with no reviews yet, or a top-critics or audience list that is still empty, returns 200 with an empty reviews array. If the feed cannot be read the service loads the movie's own review page the way a visitor's browser does and reads the list that page receives (transport: browser_render, slower, at most five pages); if that also fails for the first page, the movie page's embedded sample of about 6 reviews is served with render_error set (transport: public_page) and the call is not charged. data.subject.kind is movie, and data.movie remains present for compatibility. data.fetched_at and the X-Cache and X-Availability-Last-Success-* response headers show how fresh the data is. Pass exactly one of path or url. Supported type values are critics, top-critics, audience, and verified-audience.

Input Schema

NameRequiredDescriptionDefault
urlNoAbsolute https://www.rottentomatoes.com movie URL
pathNoRotten Tomatoes movie path
typeNoReview type: critics, top-critics, audience, verified-audience
afterNoPagination cursor: pass data.page_info.end_cursor from the previous response. Critic cursors are base64 page indexes; audience cursors are opaque keyset values that should be passed back unchanged. The feed can serve up to 500 reviews; browser fallback is capped at five pages. Invalid cursors are rejected before upstream work.
limitNoReviews per page, default 10, max 20. Keep it the same on every page of one walk: the critic cursor is a page index times this value.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.17.18
    • changedInput schema / properties / after / description
      Previous value: -"Pagination cursor from data.page_info.end_cursor"New value: +"Pagination cursor: pass data.page_info.end_cursor from the previous response. Critic cursors are base64 page indexes; audience cursors are opaque keyset values that should be passed back unchanged. The feed can serve up to 500 reviews; browser fallback is capped at five pages. Invalid cursors are rejected before upstream work."
    • changedInput schema / properties / limit / description
      Previous value: -"Reviews to return, default 10, max 20"New value: +"Reviews per page, default 10, max 20. Keep it the same on every page of one walk: the critic cursor is a page index times this value."
  2. Changed1 schema field changedv1.17.5
    • addedInput schema / properties / type / enum
      Added value: +[
+  "critics",
+  "top-critics",
+  "audience",
+  "verified-audience"
+]
  3. Addedv1.1.0

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the transport tiers (`feed_api`, then a slower `browser_render` fallback capped at five pages, then a `public_page` sample of ~6 reviews with `render_error` set and no charge), empty-result behavior (200 with empty `reviews` array), and freshness signals (`data.fetched_at`, `X-Cache`). It also warns that invalid cursors are rejected before upstream work and that the feed caps at 500 reviews.

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?

Dense and mostly front-loaded — purpose, then pagination, then fallbacks, then response shape. Minor waste: the opening line repeats the tool name twice ('Rotten Tomatoes movie reviews. Returns Rotten Tomatoes movie reviews...'), and the final sentence re-lists the enum already present in the schema.

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?

No output schema and no annotations, yet the description documents the response envelope (`data.page_info.end_cursor`, `data.transport`, `data.subject.kind`, `data.movie`, `data.fetched_at`), per-review fields, degenerate empty cases, and degradation paths. An agent has everything needed to call it and interpret the result.

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%, so the baseline is 3, but the description adds a constraint the schema does not encode: `path` and `url` are mutually exclusive and exactly one must be passed. It also restates the cursor/limit coupling for paging; the rest of the parameter detail is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Returns Rotten Tomatoes movie reviews, newest first') and names the ordering and scope. It does not, however, distinguish itself from sibling tools like rottentomatoes_critic_reviews, rottentomatoes_publication_reviews, or rottentomatoes_movie, so an agent must infer the boundary.

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?

Gives concrete invocation rules: 'Pass exactly one of `path` or `url`', the four supported `type` values, and a paging recipe (reuse `end_cursor` as `after`, keep `limit` constant). It never states when to prefer this over the critic- or publication-scoped review siblings, which is the main routing decision an agent faces.

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

Deploy Server

Other Tools