Skip to main content
Glama
Sign In

Jam

by dev.jam
OverviewDiscussionsAdmin

getFrames

Read-onlyIdempotent

Still frames from a video Jam, as images. Set mode: 'overview' for one labeled grid across the whole video (start here); 'at' with at timestamps in ms; or 'window' with count evenly spaced frames, optionally within fromMs–toMs. size sets the frame height (not for the overview). At most 30 frames a call. Videos on Cloudflare Stream only; otherwise one text block says why.

Input Schema

NameRequiredDescriptionDefault
atNoTimestamps in ms, with mode 'at'
modeNoRequired. Which frames to return. `overview`: one labeled grid spanning the whole video. `at`: the frames at the times in `at`. `window`: `count` frames evenly spaced from `fromMs` to `toMs` (whole video by default). Fields that belong to other modes are ignored. Calls from older tool lists that omit it use `overview` or the fields they set.
sizeNosmall 360p, medium 720p (default), large 1080pmedium
toMsNoWindow end in ms, with mode 'window'
countNoEvenly spaced frames, first and last included, with mode 'window'
jamIdYesJam identifier — a UUID or a jam.dev URL
fromMsNoWindow start in ms, with mode 'window'
intentNoIn 15-30 English words, your larger task and why this call helps it. People by role ("a customer"); no argument values or secrets.
overviewNoDeprecated: use `mode: "overview"`. Accepted only for clients with an older tool list.
llm_modelNoYour exact model id from your system prompt, or "unknown". Never guess.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedInput schema / properties / at / description
      Previous value: -"Timestamps in milliseconds. Required when mode is `at`; ignored otherwise."New value: +"Timestamps in ms, with mode 'at'"
    • changedInput schema / properties / count / description
      Previous value: -"Number of evenly-spaced frames. Required when mode is `window`; ignored otherwise."New value: +"Evenly spaced frames, first and last included, with mode 'window'"
    • changedInput schema / properties / fromMs / description
      Previous value: -"Optional window start in milliseconds. Defaults to 0. Used when mode is `window`; ignored otherwise."New value: +"Window start in ms, with mode 'window'"
    • changedInput schema / properties / intent / description
      Previous value: -"In 15-30 words, say what larger task you are working on and why this tool helps it. Refer to people and companies by role (\"a customer\"), and leave out argument values and secrets. Use English. Example: \"Debugging a checkout failure a customer reported, checking which network request returned the 500.\""New value: +"In 15-30 English words, your larger task and why this call helps it. People by role (\"a customer\"); no argument values or secrets."
    • changedInput schema / properties / llm_model / description
      Previous value: -"The exact model identifier you are running as, from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Pass \"unknown\" if you are not certain; never guess."New value: +"Your exact model id from your system prompt, or \"unknown\". Never guess."
    • changedInput schema / properties / size / description
      Previous value: -"Frame height: small=360p, medium=720p (default), large=1080p"New value: +"small 360p, medium 720p (default), large 1080p"
    • changedInput schema / properties / toMs / description
      Previous value: -"Optional window end in milliseconds. Defaults to the video end. Used when mode is `window`; ignored otherwise."New value: +"Window end in ms, with mode 'window'"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish that this is a read-only, idempotent, non-destructive operation. The description goes further by disclosing the 30-frame cap and the Cloudflare Stream-only limitation, including how unsupported videos are reported.

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 description is front-loaded, dense, and free of filler. Every sentence adds either mode guidance, a limit, or a platform restriction.

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?

Given the 10-parameter schema and no output schema, the description covers the key invocation constraints and return behavior well enough. It leaves intent and llm_model to the schema, which is reasonable since those are ancillary parameters.

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 every parameter. The description restates the mode and size semantics, adding only a small clarification that size does not apply to the overview.

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?

The description opens with a specific verb and resource, 'Still frames from a video Jam, as images,' and its mode breakdown makes the output and scope immediately clear. It is easily distinguishable from siblings like analyzeVideo or getVideoTranscript.

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 explicitly routes the agent to start with 'overview' and explains when to use 'at' versus 'window,' including the optional fromMs–toMs range. It adds a platform constraint, though it does not explicitly name sibling alternatives.

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

All Jam toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources