Distributed Video QA MCP

Look at frames

video_frames

Read-only

Extract frames as images at exact timestamps or evenly across a video range; use exact decoding at higher resolution to read small on-screen text.

Instructions

Frames as images, at given timestamps or spread across a range. With exact=true each is decoded from the source at that instant and at higher resolution than the indexed samples, for reading small text.

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": {
      "video_id": "<video_id>"
    },
    "name": "video_frames"
  }
}

Input Schema

Name	Required	Description
`end`	No	...to this second.
`count`	No	Frames across start..end.
`exact`	No	Decode at the exact instant from the source file.
`start`	No	Or: evenly spaced frames from this second...
`image_px`	No	Long side of returned images, in pixels.
`video_id`	Yes	Video id from video_list or an ingest result.
`timestamps`	No	Exact seconds, up to 12.

Output Schema

Name	Required	Description
`exact`	Yes	True when frames were decoded from the source at the exact instant.
`title`	Yes	Its title.
`frames`	Yes	Attached as images after the JSON in this order.
`video_id`	Yes	The video.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 13, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: exact=true decodes from the source file at that instant at higher resolution than the indexed samples, which signals a fidelity/cost tradeoff an agent would otherwise not know. It omits any note on latency or payload implications of the larger resolution, which is the remaining gap.

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?

Two dense sentences with no filler, and the primary capability is front-loaded before the exact=true qualifier. The opening is slightly telegraphic ('Frames as images, at given timestamps or spread across a range'), which costs a little clarity but wastes no words.

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?

Seven parameters are a meaningful surface, but an output schema exists and annotations are present, so the description need not explain returns or safety. It covers the selection modes and the exact-decode tradeoff, which are the decisions an agent must make; only the mutual exclusivity of timestamps versus start/end is left implicit.

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 and the schema already explains each parameter. The description does add some meaning beyond the schema by framing timestamps versus start/end as two alternative modes and by explaining why exact decoding matters. The two sentences do not explicitly cover image_px or count, but the schema handles those adequately.

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 resource and output form: 'Frames as images', with two selection modes (timestamps or a range). An agent can tell this returns image frames rather than metadata, transcripts, or clips. It stops short of naming a sibling to contrast with, so it is clear but not fully differentiated.

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 is implied rather than stated: the exact=true sentence gives a concrete use case ('for reading small text'), which tells the agent when the higher-fidelity mode matters. There is no explicit when-not guidance and no routing to alternatives such as image-based search, so the agent must infer the boundary.

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