SceneF — California, Florida and Hawaii Movie Showtimes

The accuracy record

scenef_accuracy

Read-onlyIdempotent

Returns SceneF's verification record: this board's confidence mix, the counts of verification checks confirmed / missing / unreachable over the record's window (window_days in the payload — 30 days at present) with the pass rate and the exact denominator it was computed from, the same per venue with source tier and last-verified time, and the definitions of every level. Checks that could not run — a bot wall, a client-rendered page — are graded unreachable and excluded from the pass rate rather than counted as passes. Quote these numbers directly; they are recomputed on every call. Read-only: the call itself records nothing.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`region`	No	Which regional board to read: a board id such as "sf", "oahu" or "miami", not a city name ("Honolulu" or "Chicago" is rejected). Omitted means "sf" (San Francisco); it is never inferred from where you are. For a city, ZIP or neighborhood call scenef_resolve_board first; scenef_now with no region lists every id. An unknown region is an error, not a fallback.
`response_format`	No	Output size. "concise" (default) is tight text plus a structured summary. In whats_playing, each film has the total showtime_count, next_showtime, and a showtimes array containing only that next screening; "detailed" adds showtime rows with ids, ticket urls and accuracy metadata, about 200 across the answer. film_details and search_showtimes return the 40 nearest showtimes in "concise" and up to 200 in "detailed". showtime_count is always the total and showtimes_complete says whether the array is all of it; narrow by date or theater for the rest.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`docs`	Yes
`site`	Yes
`method`	Yes
`region`	Yes
`venues`	Yes
`timezone`	Yes
`data_as_of`	Yes
`attribution`	Yes
`region_name`	Yes
`accuracy_url`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 2, 2026

changedInput schema / properties / region / description

Previous value: -"Which regional board to read, e.g. \"sf\", \"oahu\", \"sacramento\". Omitted means the default board — it is never inferred from where you are. Call scenef_now for the full list; an unknown region is an error, not a fallback."New value: +"Which regional board to read: a board id such as \"sf\", \"oahu\" or \"miami\", not a city name (\"Honolulu\" or \"Chicago\" is rejected). Omitted means \"sf\" (San Francisco); it is never inferred from where you are. For a city, ZIP or neighborhood call scenef_resolve_board first; scenef_now with no region lists every id. An unknown region is an error, not a fallback."

addedInput schema / properties / region / maxLength
```
Added value: +120
```

changedInput schema / properties / response_format / description

Previous value: -"Output size. \"concise\" (default) is tight text plus a structured summary. In whats_playing, each film has the total showtime_count, next_showtime, and a showtimes array containing only that next screening; showtimes_complete says whether the array is exhaustive. \"detailed\" includes all selected showtime rows with ids, ticket urls, and accuracy metadata. Use scenef_search_showtimes for all times for one film or theatre."New value: +"Output size. \"concise\" (default) is tight text plus a structured summary. In whats_playing, each film has the total showtime_count, next_showtime, and a showtimes array containing only that next screening; \"detailed\" adds showtime rows with ids, ticket urls and accuracy metadata, about 200 across the answer. film_details and search_showtimes return the 40 nearest showtimes in \"concise\" and up to 200 in \"detailed\". showtime_count is always the total and showtimes_complete says whether the array is all of it; narrow by date or theater for the rest."

Changed6 schema fields changedSep 18, 2026

changedInput schema / properties / response_format / description

Previous value: -"Output size. \"concise\" (default) is tight text plus a structured summary — on list-shaped tools each film carries showtime_count and next_showtime, but NOT the full showtimes array. \"detailed\" adds the per-showtime rows with ids, ticket urls, and accuracy metadata. Concise measures ~10KB where detailed measures ~69KB, so ask for detailed when you need the rows and scenef_search_showtimes when you need them for one film or theatre."New value: +"Output size. \"concise\" (default) is tight text plus a structured summary. In whats_playing, each film has the total showtime_count, next_showtime, and a showtimes array containing only that next screening; showtimes_complete says whether the array is exhaustive. \"detailed\" includes all selected showtime rows with ids, ticket urls, and accuracy metadata. Use scenef_search_showtimes for all times for one film or theatre."

addedOutput schema / properties / accuracy_url
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / region
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / region_name
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / timezone
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / required

Previous value: -[
-  "data_as_of",
-  "attribution",
-  "site",
-  "venues",
-  "method",
-  "docs"
-]New value: +[
+  "data_as_of",
+  "attribution",
+  "accuracy_url",
+  "region",
+  "region_name",
+  "timezone",
+  "site",
+  "venues",
+  "method",
+  "docs"
+]

Changed1 schema field changedSep 8, 2026

changedInput schema / properties / response_format / description

Previous value: -"Output size: \"concise\" (default) for tight text lines, \"detailed\" to add ids, per-showtime ticket urls, and extra metadata."New value: +"Output size. \"concise\" (default) is tight text plus a structured summary — on list-shaped tools each film carries showtime_count and next_showtime, but NOT the full showtimes array. \"detailed\" adds the per-showtime rows with ids, ticket urls, and accuracy metadata. Concise measures ~10KB where detailed measures ~69KB, so ask for detailed when you need the rows and scenef_search_showtimes when you need them for one film or theatre."

Changed1 schema field changedSep 6, 2026

addedInput schema / properties / region

Added value: +{
+  "description": "Which regional board to read, e.g. \"sf\", \"oahu\", \"sacramento\". Omitted means the default board — it is never inferred from where you are. Call scenef_now for the full list; an unknown region is an error, not a fallback.",
+  "type": "string"
+}

First observedAug 11, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations: it discloses that unreachable checks (bot walls, client-rendered pages) are excluded from the pass rate rather than counted as passes, that the window is 30 days via window_days, that the exact denominator is returned, and that the call itself records nothing. That is meaningful behavioral context an agent cannot get from annotations.

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?

A single dense paragraph that front-loads what is returned before the grading rules and the read-only note. It is longer than typical but nearly every clause carries information — only the 'quote these numbers directly' instruction borders on filler.

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?

An output schema exists so return shape need not be restated, yet the description usefully previews the payload (confidence mix, counts, per-venue tier, level definitions). Combined with the region semantics in the schema, an agent has enough to call it correctly; the only real gap is when-not-to-use guidance.

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 description coverage is 100%, and the schema fully documents region semantics (board id vs city name, default sf) and response_format. The description adds no parameter-level guidance beyond mentioning window_days as payload content, so the baseline 3 applies.

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?

States a specific verb and resource: returns SceneF's verification/accuracy record with confidence mix, check counts, pass rate, per-venue breakdown and level definitions. That is clearly distinct from siblings like scenef_whats_playing or scenef_now, so an agent can differentiate it 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 Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives useful usage context (quote these numbers directly, recomputed every call, read-only), but never states when to prefer this tool over alternatives such as scenef_now for read-status checks, nor any exclusions. Usage is implied rather than prescribed.

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

All SceneF — California, Florida and Hawaii Movie Showtimes tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?