Skip to main content
Glama

omniseek_view

Read-only

View document figures, image URLs, and video frames by returning image blocks or contact sheets for visual inspection and analysis.

Instructions

SEE with your own vision, IN-BAND: document figures, loose image URLs, or video frames.

Tool name: omniseek_view (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_view".

kind="auto" sends a document path or extension to document figures, a video URL (youtube, bilibili, douyin, .mp4/.webm/.mov) to frames, anything else to image URLs.

Args: target: document path or URL, video URL, or image URLs separated by commas, spaces or newlines. kind: "auto" | "document" | "images" | "video". sections: (document) slide or page numbers, comma-separated; "" = all. names: (document) exact image names from omniseek_read's outline media[].name. render_pages: (PDF) whole pages to render, for vector figures and tables with no embedded image. max_images: full-resolution cap; a wider selection comes back as a contact sheet. contact_sheet: (document) always return one tiled contact sheet. start: (video) slice start, e.g. "8:30" or "90". duration: (video) slice length; default the whole video, capped at 30 minutes. n: (video) frames to sample (default 12, max 24).

Returns image blocks: a contact sheet with a legend, or a manifest plus one block per image; or an error or "nothing to show" note. Usual flow: omniseek_read for the outline, this with no selection for a contact sheet, then the figures that matter by sections or names. More: omniseek docs/TOOLS.md, omniseek_view.

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": {
      "target": "<target>"
    },
    "name": "omniseek_view"
  }
}

Input Schema

NameRequiredDescriptionDefault
nNo
kindNoauto
namesNo
startNo
targetYes
durationNo
sectionsNo
max_imagesNo
render_pagesNo
contact_sheetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.7/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, and the description adds real behavior beyond that: the return shape (contact sheet with legend, or a manifest plus one block per image, or a 'nothing to show' note), the max_images full-resolution cap that downgrades a wide selection to a contact sheet, and video slicing limits (default whole video, capped at 30 minutes, n default 12 max 24). It does not discuss context/payload cost of many image blocks or any rate limits, which is the remaining gap for a media-heavy read.

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 purpose statement and the args block are front-loaded and every arg line earns its place. Some overhead is spent on meta-instructions (MCP prefix warning, ToolSearch fallback, docs pointer) that are not about invoking the tool, which keeps it from being maximally tight.

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

Completeness5/5

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

For a 10-parameter, no-output-schema tool the description covers the full lifecycle: dispatch on kind=auto, per-parameter semantics, the return formats including error and empty cases, and the sequencing with omniseek_read. An agent has enough to call this correctly on the first attempt without opening docs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 10 parameters, so the description must carry the load and it does: every parameter is explained with meaning and, where relevant, format or default (start accepts "8:30" or "90", duration capped at 30 minutes, n default 12 max 24, sections "" means all, names must be exact from omniseek_read's outline media[].name). It also supplies enum-like values for kind that the schema leaves unconstrained.

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 opening line states a specific verb and resource: retrieve visual content (document figures, standalone image URLs, video frames) and return it as in-band image blocks. It also implicitly separates itself from the text-oriented sibling by referencing omniseek_read's outline as the source of image names, so an agent can tell which tool yields pixels versus prose.

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

Usage Guidelines5/5

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

It gives explicit routing rules for kind="auto" (document path or extension → document figures; video URL or .mp4/.webm/.mov → frames; anything else → image URLs) and a concrete recommended workflow: omniseek_read for the outline, this tool with no selection for a contact sheet, then specific sections or names. That is when-to-use plus the alternative it pairs with, not just implied usage.

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