Skip to main content
Glama

Read the AI summary and chapters

get_summary
Idempotent

Retrieves a Recordful video's AI summary and timestamped chapters, or generates them when missing after user approval using workspace AI credits.

Instructions

Recordful Pro only. A Recordful video's AI summary (2 to 4 sentences) and chapters ([{ startSeconds, title }], the first at 0), as shown on its page. Reading is free. If there is none (status "none"), writing one spends the workspace's AI credits (about 1 to 2 a summary): ask the user first, then call with generate: true. Needs a transcript (status "no_transcript": call get_transcript first). OUT_OF_CREDITS means none are left this month. Defaults to the last recording.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_summary"
  }
}

Input Schema

NameRequiredDescriptionDefault
videoIdNoRecordful video ID (from stop_recording, upload_recording or list_videos). Defaults to the last recording.
generateNoWrite one if there is none yet. It spends the workspace's AI credits: only after the user said yes.
regenerateNoWrite a new one even if one exists (spends credits; only after the user said yes).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false and idempotentHint=true, which the description explains: reads are free, but generate/regenerate spend the workspace's AI credits (about 1-2 per summary) and require user consent. It goes further than the annotations by disclosing status values ('none', 'no_transcript'), the OUT_OF_CREDITS error meaning, and the default-to-last-recording behavior.

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 plan gate, the resource, the free-read fact, and the two conditional branches are front-loaded and each sentence carries decision-relevant information. It is dense and parenthetical (the inline array shape and credit estimate), which slightly hurts scanability but never wastes words.

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?

There is no output schema, yet the description specifies the return contents and structure, the status values, and the error code an agent may hit. For a tool with a write path gated on credits and a transcript prerequisite, everything needed to call it correctly is present.

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 the baseline is 3, and the description earns a notch above by tying the generate flag to a precondition (status 'none' plus explicit user approval) and to the credit cost. It does not add meaning for regenerate beyond what the schema already says, and videoId's default is merely repeated.

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 names a specific verb+resource (read a video's AI summary and chapters) and states the exact return shape: 2-4 sentences plus a chapters array of {startSeconds, title} with the first at 0. It also distinguishes itself from the sibling get_transcript by framing that tool as a prerequisite rather than an alternative.

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 when/when-not rules: read freely if a summary exists, ask the user first and call with generate:true only if status is 'none', and call get_transcript first if status is 'no_transcript'. The plan gate (Recordful Pro only) and the cost trigger are stated up front, leaving little to inference.

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