Skip to main content
Glama
Sign In

FrameThrower

by ai.framethrower
OverviewDiscussionsAdmin

get_animation_sequence

Read-only

A frame in its sequence: the shots just before and after it in the same episode / film, in order, each with its still and caption — to see how a moment is built, or to lay a beat out across several canvas panels. With clips: true, each shot's clip plus the continuous "run" video that covers them (run_url, with from/to seconds).

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": {
      "frame_id": "<frame_id>"
    },
    "name": "get_animation_sequence"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterNodefault 2
clipsNotrue = also return each frame's clip and sequence videos (the call costs 8 credits). Ask only when the user wants to see it move.
beforeNodefault 2
frame_idYesA frame id from earlier results (or "slug:label")

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare readOnly and openWorld, so the description carries the real weight: it discloses that results come back ordered, that each entry carries a still and caption, and that clips=true yields both per-shot clips and a continuous run video with from/to seconds. The credit cost (8) lives in the schema rather than here, which is a minor missed opportunity.

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 sentence that front-loads the core concept (frame in its sequence) before the optional clips behavior. The em-dash clause justifies usage efficiently; nothing is redundant, though the sentence is long enough that a second break would aid scanning.

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?

With no output schema, the description steps in to define the return payload (ordered shots, stills, captions, run_url with from/to). Edge behavior at sequence boundaries (fewer than N neighbors) and whether ordering spans scene cuts are not addressed, which is a modest gap for a sequence tool.

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 a 3 is the floor, and the description earns above that by explaining what clips=true actually produces (per-shot clip plus a covering run video with from/to offsets) beyond the schema's terser 'sequence videos'. It says nothing about before/after semantics, but those are self-documenting with defaults and bounds 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?

The description states a specific verb and resource: it returns the shots immediately before and after a given frame within the same episode or film, each with its still and caption. This clearly separates it from get_frame_details (single frame) and search_animation_frames (discovery), though it never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

It gives two concrete use cases ('to see how a moment is built' and 'to lay a beat out across several canvas panels') and conditions for the clips flag ('Ask only when the user wants to see it move'). It does not explicitly exclude the neighboring detail/similarity tools, so an agent still has to infer the boundary.

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

All FrameThrower 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