Skip to main content
Glama

film

Idempotent

Seal a past window of the tape into a FILM: the bars replayed one by one with the trader's drawings and marked levels, optionally the structure computed over the bars (pivots, legs, swings and the range they share, none drawn before the bar that confirmed it) and a rehearsed machine's trades. Returns the film's public link, where it plays and can be downloaded as a video. 24 to 360 bars; the window must be in the past. A film is a replay of what printed: say so, and never present it as a forecast.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "market": "<market>",
      "tf": "<tf>",
      "from": "<from>",
      "to": "<to>"
    },
    "name": "film"
  }
}

Input Schema

NameRequiredDescriptionDefault
tfYestimeframe
toYeswindow end, ISO-8601 UTC, in the past
fromYeswindow start, ISO-8601 UTC
marksNoinclude the trader's marked levels (default true)
titleNoa short name beside the wordmark
kickerNoa short line at the right, e.g. price → structure
marketYesthe market
revealNoshow those scripts' rules (their transitions' conditions in plain words and their params) to anyone with the link. Only when the trader explicitly asks to reveal them; never by default
machineNoinclude the trades of the trader's rehearsed machine on this market, labelled a rehearsal
paletteNothe inks
scriptsNoup to two of the trader's OWN kept cubicle.scripts, by name: each is run over the window and filmed as it acted (state band, entries and exits, stop, target and trail, its running result), labelled a rehearsal, with chapters at its moments
secondsNolength, 8 to 40 seconds (default 18)
drawingsNoinclude the trader's drawings (default true)
headlineNothe headline's first part (drawn in parchment), at most 44 characters
structureNodraw the computed structure and name the chapters after it
headline_goldNothe headline's second part (drawn in gold)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / reveal
      Added value: +{
      +  "description": "show those scripts' rules (their transitions' conditions in plain words and their params) to anyone with the link. Only when the trader explicitly asks to reveal them; never by default",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / scripts
      Added value: +{
      +  "description": "up to two of the trader's OWN kept cubicle.scripts, by name: each is run over the window and filmed as it acted (state band, entries and exits, stop, target and trail, its running result), labelled a rehearsal, with chapters at its moments",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / tf / enum
      Previous value: -[
      -  "15s",
      -  "1m",
      -  "5m",
      -  "15m",
      -  "1h",
      -  "4h",
      -  "1d"
      -]New value: +[
      +  "1s",
      +  "15s",
      +  "1m",
      +  "5m",
      +  "15m",
      +  "1h",
      +  "4h",
      +  "1d"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / tf / enum
      Previous value: -[
      -  "15s",
      -  "1m",
      -  "5m",
      -  "1h"
      -]New value: +[
      +  "15s",
      +  "1m",
      +  "5m",
      +  "15m",
      +  "1h",
      +  "4h",
      +  "1d"
      +]
  4. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare non-destructive, non-readOnly, idempotent, so the safety profile is covered. The description adds behaviour beyond that: the output is a public link anyone can open and download, the render is bounded to 24-360 bars and to past windows, and scripted runs are labelled a rehearsal. It does not mention render cost, latency, or persistence/expiry of the link, which keeps it from a 5.

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 output and the key constraint are front-loaded, and the closing sentence carries an important framing rule with no padding. The first sentence is heavily parenthetical and stretched, and ornamental phrasings like 'the inks' or 'drawn in parchment' cost the reader without adding selection value.

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?

For a 16-parameter render tool with no output schema, the description covers what is produced (a public link to a downloadable video), the validity window, and the framing guardrail against presenting a replay as a forecast. Remaining gaps — cost, render time, link lifetime — are operational rather than selection-critical.

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 baseline is 3, and the description does add real meaning for several toggles — structure (pivots, legs, swings, nothing drawn before the confirming bar), scripts (up to two of the trader's own kept scripts, filmed as they acted, with chapters), and the 24-360 bar window constraint that spans parameters. It adds meaning over the schema but does not walk through the 16 parameters, leaving headline/palette/kicker/seconds to the schema alone.

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?

The description states a specific verb and artifact: seal a past window of bars into a film that 'plays and can be downloaded as a video', returning a public link. That is concrete enough for an agent to know it produces a shareable rendered video replay. The metaphoric opening ('seal a past window of the tape') and lack of a named contrast with siblings like chart_image or replay_record keep it short of a 5.

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?

Usage constraints are stated (24 to 360 bars, the window must be in the past), which tells the agent when the call is valid. However, there is no explicit routing guidance such as 'use chart_image for a still picture' or 'use replay_record for the raw data' — the nearest signal is the negative framing 'never present it as a forecast'. Selection among siblings 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources