Skip to main content
Glama

rottentomatoes_movie_reviews

Read-only

Fetch Rotten Tomatoes reviews for one movie, newest first. Critics, top critics, audience and verified-audience all return the full review feed with stable review ids, ISO created_at and updated_at times, critic identity and the original article URL, limit reviews per page, pageable with the returned end_cursor up to 500 reviews deep (keep limit the same while paging). A title with no reviews yet returns an empty list. If the feed cannot be read the service renders the public review page instead, which is slower and pageable for up to five pages, and as a last resort it returns the small sample the movie page embeds, marked with render_error and not charged. Pass exactly one movie path or URL; type selects critics, top-critics, audience, or verified-audience. limit defaults to 10, capped at 20. fetched_at gives the fetch time of the data, and transport says which path served the response. Use rottentomatoes_movie for movie metadata and scorecards.

Input Schema

NameRequiredDescriptionDefault
urlNoAbsolute https://www.rottentomatoes.com movie URL
pathNoRotten Tomatoes movie path
typeNoReview type: critics, top-critics, audience, verified-audience. Documented values: 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.

Output Schema

NameRequiredDescriptionDefault
dataYesThe tool result payload (shape varies per tool; see each tool's docs resource).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / after / description
      Previous value: -"Pagination cursor: pass data.page_info.end_cursor from the previous response. Critic cursors are base64 page indexes, the list can be paged up to 500 reviews deep at any limit, and the cursor must be used with the same limit that produced it; audience cursors are opaque. An invalid or too-deep cursor is rejected before any upstream work."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."
  2. Changed2 schema fields changed
    • changedInput schema / properties / after / description
      Previous value: -"Pagination cursor: pass data.page_info.end_cursor from the previous response. Cursors are page indexes (base64), the deepest supported cursor is page 5 (100 reviews), and each deeper page costs one extra Load More click in the browser session."New value: +"Pagination cursor: pass data.page_info.end_cursor from the previous response. Critic cursors are base64 page indexes, the list can be paged up to 500 reviews deep at any limit, and the cursor must be used with the same limit that produced it; audience cursors are opaque. An invalid or too-deep cursor is rejected before any upstream work."
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum reviews to return, default 10, max 20. Critic pages hold 20; the audience sample holds about 6, so fewer may come back."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."
  3. Changed2 schema fields changed
    • changedInput schema / properties / after / description
      Previous value: -"Pagination cursor. Currently unavailable: responses carry no data.page_info.end_cursor, and any value returns 503."New value: +"Pagination cursor: pass data.page_info.end_cursor from the previous response. Cursors are page indexes (base64), the deepest supported cursor is page 5 (100 reviews), and each deeper page costs one extra Load More click in the browser session."
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum reviews to return, default 10, max 20. The movie page typically supplies about 6, so fewer may come back."New value: +"Maximum reviews to return, default 10, max 20. Critic pages hold 20; the audience sample holds about 6, so fewer may come back."
  4. Changed2 schema fields changed
    • changedInput schema / properties / after / description
      Previous value: -"Pagination cursor from data.page_info.end_cursor"New value: +"Pagination cursor. Currently unavailable: responses carry no data.page_info.end_cursor, and any value returns 503."
    • changedInput schema / properties / limit / description
      Previous value: -"Reviews to return, default 10, max 20"New value: +"Maximum reviews to return, default 10, max 20. The movie page typically supplies about 6, so fewer may come back."
  5. Changed5 schema fields changed
    • addedInput schema / properties / after / description
      Added value: +"Pagination cursor from data.page_info.end_cursor"
    • addedInput schema / properties / limit / description
      Added value: +"Reviews to return, default 10, max 20"
    • addedInput schema / properties / path / description
      Added value: +"Rotten Tomatoes movie path"
    • addedInput schema / properties / type / description
      Added value: +"Review type: critics, top-critics, audience, verified-audience. Documented values: critics, top-critics, audience, verified-audience."
    • addedInput schema / properties / url / description
      Added value: +"Absolute https://www.rottentomatoes.com movie URL"
  6. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover readOnly/openWorld, but the description adds substantial behavioral detail beyond them: the browser-render fallback (slower, capped at five pages) and the last-resort embedded sample marked render_error and not charged. It also discloses the 500-review depth limit and paging stability requirement, which the annotations do not convey.

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?

Front-loads purpose and paging/fallback semantics before the sibling pointer, and every sentence carries information. It is dense and slightly run-on in the fallback/telemetry clauses, but nothing is wasted.

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?

With an output schema present, return values need not be described, and the description covers scoping, pagination depth, fallback behavior, and the sibling alternative. Nothing an agent needs to call this correctly is missing.

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 coverage is 100%, so the schema already documents all five parameters thoroughly. The description reinforces limit defaults/caps and the keep-limit-stable paging rule, but this largely restates what the schema's rich descriptions already say, so it does not add much 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?

Opens with a specific verb and resource ('Fetch Rotten Tomatoes reviews for one movie, newest first'), and distinguishes itself from rottentomatoes_movie (metadata/scorecards) and the type-specific feeds it exposes. An agent can identify the tool and its scope without opening the schema.

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?

Explicitly routes the agent: use rottentomatoes_movie for movie metadata and scorecards, and use 'type' to pick critics/top-critics/audience/verified-audience. It also states the exactly-one-of path/URL rule, which is a concrete usage constraint rather than implied 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.