Skip to main content
Glama
Sign In

txtreel

by com.txtreel
OverviewDiscussionsAdmin

Screenshot a txtreel conversation

chat_screenshot

Render a single frame of a txtreel conversation (script or messages) to a PNG and return it as an image. Defaults to the last frame — pass "frame" to capture an earlier moment (30 fps).

Returns the PNG as image content, plus a text line with the PNG's URL (expires after 24 hours).

Conversation script format (one event per line):

them: hey, you up? me: yeah why [pause 1.5] wait 1.5 s --- Today 9:41 PM date/time separator me: [photo URL] caption a photo (URL, local file path, or an uploaded photo's number) [them reacts ❤️] reaction on my last message [read] they read my messages === everything above is already on screen at the start === scroll 3 same, but open on the oldest message and skim down in 3 s

comment

"Name: text" also means "them" when Name matches contact.name (e.g. contact.name "Sam" lets you write "Sam: omg" instead of "them: omg"). A literal "\n" inside a message becomes a line break. Lines starting with # are comments.

Photos: "me: [photo https://example.com/image.jpg] optional caption" (https URLs only; local file paths are not available). "=== scroll 3" opens on the oldest message of a longer history and skims down to the live part in 3 s. With keyboard true (the default), the newest messages stay above the area where the Reels caption sits.

Input Schema

NameRequiredDescriptionDefault
frameNoFrame index to capture, at 30 fps (e.g. 30 = one second in). Omit to capture the final frame of the conversation.
speedNoPacing multiplier; 2 = twice as fast, 0.5 = half speed. Default: 1.
themeNoColor theme, "light" or "dark". Default: light.
scriptNoConversation as a plain-text script. Use this OR messages, not both. Conversation script format (one event per line): them: hey, you up? me: yeah why [pause 1.5] wait 1.5 s --- Today 9:41 PM date/time separator me: [photo URL] caption a photo (URL, local file path, or an uploaded photo's number) [them reacts ❤️] reaction on my last message [read] they read my messages === everything above is already on screen at the start === scroll 3 same, but open on the oldest message and skim down in 3 s # comment "Name: text" also means "them" when Name matches contact.name (e.g. contact.name "Sam" lets you write "Sam: omg" instead of "them: omg"). A literal "\n" inside a message becomes a line break. Lines starting with # are comments. Photos: "me: [photo https://example.com/image.jpg] optional caption" (https URLs only; local file paths are not available). "=== scroll 3" opens on the oldest message of a longer history and skims down to the live part in 3 s. With keyboard true (the default), the newest messages stay above the area where the Reels caption sits.
soundsNoReal UI sounds: iOS key clicks while typing, the app's send and receive sounds. Default: true.
contactNoContact header info.
endHoldNoSeconds to hold on the final frame before the video ends. Default: 2.
autoReadNoMark "me" messages as read as soon as the other person starts typing. Default: true.
keyboardNoShow the iOS keyboard, which keeps the latest messages above the Reels caption area. Default: true.
messagesNoConversation as an array of event objects instead of a script string (use this OR script, not both). Passed through to the txtreel API as-is; each item is one of: {from:"me"|"them", text, delay?, typing?, hold?, time?, instant?} (type "message" is the default and can be omitted), {type:"pause", seconds}, {type:"timestamp", text, instant?}, {type:"read", time?}, {type:"react", from:"me"|"them", emoji}.
platformNoChat app to render: "imessage", "whatsapp", or "instagram". Default: imessage.
startTimeNoClock used for messages, read receipts, and WhatsApp bubble times, e.g. "9:41 PM". Default: 9:41 PM.
statusBarNoPhone status bar shown at the top of the frame.
composerTypingNoType "me" messages into the input bar before sending them. Default: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / script / description
      Previous value: -"Conversation as a plain-text script. Use this OR messages, not both.\n\nConversation script format (one event per line):\n\nthem: hey, you up?\nme: yeah why\n[pause 1.5]            wait 1.5 s\n--- Today 9:41 PM      date/time separator\nme: [photo URL] caption a photo (URL, local file path, or an uploaded photo's number)\n[them reacts ❤️]       reaction on my last message\n[read]                 they read my messages\n===                    everything above is already on screen at the start\n=== scroll 3           same, but open on the oldest message and skim down in 3 s\n# comment\n\n\"Name: text\" also means \"them\" when Name matches contact.name (e.g. contact.name \"Sam\" lets you write \"Sam: omg\" instead of \"them: omg\"). A literal \"\\n\" inside a message becomes a line break. Lines starting with # are comments.\n\nGuidance: one short message per line, like real texting — split up what a real person would send as separate texts rather than one long paragraph. A typical reel is 8-16 messages and 15-30 seconds. Use \"[pause N]\" to hold a beat before a reply lands (dramatic timing). Use \"===\" to start the video with everything above it already on screen, e.g. for a \"catch up on this conversation\" reel. Photos: \"me: [photo https://example.com/image.jpg] optional caption\" (https URLs only; local file paths are not available). Use \"=== scroll 3\" instead to open on the oldest message of a longer history and skim down to the live part in 3 s — too fast to read, so viewers pause and rewind (good for comments: hide a detail in the history). Leave keyboard at its default (true) so the newest messages stay above where the Reels caption/UI usually sits."New value: +"Conversation as a plain-text script. Use this OR messages, not both.\n\nConversation script format (one event per line):\n\nthem: hey, you up?\nme: yeah why\n[pause 1.5]            wait 1.5 s\n--- Today 9:41 PM      date/time separator\nme: [photo URL] caption a photo (URL, local file path, or an uploaded photo's number)\n[them reacts ❤️]       reaction on my last message\n[read]                 they read my messages\n===                    everything above is already on screen at the start\n=== scroll 3           same, but open on the oldest message and skim down in 3 s\n# comment\n\n\"Name: text\" also means \"them\" when Name matches contact.name (e.g. contact.name \"Sam\" lets you write \"Sam: omg\" instead of \"them: omg\"). A literal \"\\n\" inside a message becomes a line break. Lines starting with # are comments.\n\nPhotos: \"me: [photo https://example.com/image.jpg] optional caption\" (https URLs only; local file paths are not available). \"=== scroll 3\" opens on the oldest message of a longer history and skims down to the live part in 3 s. With keyboard true (the default), the newest messages stay above the area where the Reels caption sits."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations cover safety (destructiveHint=false, openWorldHint=false), and the description adds real context beyond them: the concrete return shape (PNG image content plus a text line with a URL) and the 24-hour URL expiry. It omits auth requirements and any rendering cost/rate-limit notes, which would have pushed it higher.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence front-loads what it does, the frame default, and the return format before any format detail, so a reader can stop early. The remaining bulk is a DSL specification, which is dense but each line earns its place as syntax documentation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter, nested-object tool with no output schema, the description admirably covers the script DSL and the return payload. It is still incomplete on the workflow side: no mention of the chat_validate sibling for checking scripts before rendering, and no guidance on script vs messages trade-offs beyond 'not both'.

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%, so the baseline is 3; every parameter is already documented in the schema. The script-format prose in the description largely duplicates the schema's own 'script' description verbatim, adding little new semantic meaning.

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 — 'Render a single frame of a txtreel conversation (script or messages) to a PNG' — and the 'single frame' framing implicitly separates it from chat_render_video without opening either schema. An agent knows immediately this produces a still image, not a video.

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?

Explains the frame default and the script-vs-messages mutual exclusion ('use this OR messages, not both'), which is genuine routing guidance. However, it never says when to prefer this over chat_render_video or to run chat_validate first, so sibling selection is left to inference.

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

All txtreel toolsInspect
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