Skip to main content
Glama

get_lesson_slides

Automatically detect slide changes in lesson videos and capture one frame per slide, returning timestamps and images for note-taking.

Instructions

Auto-detect slide changes in a lesson video and return one frame per slide.

Args: course_slug: from list_enrolled_courses. lesson_slug: from list_lessons. threshold: 0..1 scene-change sensitivity. 0.3 catches slide changes; raise to 0.5+ to only cut on very distinct visuals. max_frames: cap total frames returned. Prevents very long lectures from swamping the response. min_gap_seconds: skip candidates that fall within this many seconds of the previously kept frame — suppresses near-duplicates from small on-camera movements while the slide hasn't changed. 0 disables the dedup. save_dir: if set, write each JPEG to this directory (created if missing). Filenames are "{course_slug}--{lesson_slug}--{index:03d}-{seconds}s.jpg". Absolute saved paths are included in the JSON summary so downstream tools can reference them. include_images: default True. Set False to get only timestamps + saved paths (structured data), skipping inline image content — useful for building a chapter index without image tokens.

Returns a JSON summary block first (course/lesson/frame list with timestamps and saved paths), then per-frame caption + inline image unless include_images=False. Requires ffmpeg.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
save_dirNo
thresholdNo
max_framesNo
course_slugYes
lesson_slugYes
include_imagesNo
min_gap_secondsNo
Install Server

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses return structure, side effects (writing JPEGs to save_dir), parameter effects (threshold, min_gap_seconds dedup), and the ffmpeg dependency. It also explains include_images behavior for token-conscious use.

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?

Though lengthy, the structure is efficient: a one-sentence summary, an Args list with line-per-parameter detail, and a crisp description of return format and dependencies. Every sentence earns its place, and the most important 'auto-detect' behavior is front-loaded.

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?

The description is complete for a tool with no output schema and no annotations. It explains the return order (JSON summary then caption+image), how to disable images, file side effects, and the external ffmpeg requirement. Nothing essential for calling the tool correctly is missing.

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%, so the description must compensate. It explains every parameter, including tuning guidance for threshold, what max_frames caps, how min_gap_seconds suppresses duplicates, filename pattern for save_dir, and the purpose of include_images. This exceeds what the schema alone provides.

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 sentence, 'Auto-detect slide changes in a lesson video and return one frame per slide,' states a specific verb and resource. It clearly differentiates from sibling tools like get_lesson_frame by focusing on automatic detection across an entire lesson rather than a single frame.

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?

The description implies its use case ('Auto-detect slide changes') and references list_enrolled_courses and list_lessons for slugs, but it never explicitly states when to use this tool versus get_lesson_frame or get_lesson_transcript. There are no exclusions or alternative routing.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sibtihaj/notetaker-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server