Skip to main content
Glama

package_video

Read-only

Help the signed-in user PACKAGE a YouTube video: generate several title options and thumbnail text ideas, or score a title/thumbnail they already have, always as a title+thumbnail UNIT (making sure the two complement and do not just repeat each other), grounded in the packaging that already converts on their own YouTube channel. Call this whenever the user wants help with a title or a thumbnail, wants title options or thumbnail text, asks to package or repackage a video, or wants their title/thumbnail reviewed, scored, or improved. Pass video to package or critique an existing upload of theirs (by its title), idea to generate packaging for a new idea or topic, BOTH video and idea for a follow-up or sequel to one of their videos (the new video's packaging, grounded in the one it follows), and/or title/thumbnail_text to score ones they paste. For judging whether an idea is worth making at all, use evaluate_idea; to brainstorm video ideas from scratch, use suggest_ideas; for the general pattern across their best thumbnails, use find_best_thumbnails.

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": "package_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
ideaNoA new video idea or topic to generate packaging for. Combine with `video` when it follows on from that upload
titleNoA proposed title to score
topicNo
videoNoAn existing upload of theirs to package or critique (its title or part of it). Combine with `idea` for a follow-up to it
thumbnail_textNoProposed thumbnail text to score

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed2 schema fields changed
    • changedInput schema / properties / idea / description
      Previous value: -"A new video idea or topic to generate packaging for"New value: +"A new video idea or topic to generate packaging for. Combine with `video` when it follows on from that upload"
    • changedInput schema / properties / video / description
      Previous value: -"An existing upload of theirs to package or critique (its title or part of it)"New value: +"An existing upload of theirs to package or critique (its title or part of it). Combine with `idea` for a follow-up to it"
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is known. The description adds real behavioral context beyond that: output is grounded in packaging that already converts on the user's own channel, and results are either generated options or scores, with no destructive mutation implied. It stops short of describing the shape of the returned scores or how many title options come back, which matters since there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and the key title+thumbnail-unit constraint are front-loaded, which is good. However, the long trigger sentence enumerating title, thumbnail, package, repackage, review, score, and improve largely restates the first sentence, and the whole definition is delivered as one dense paragraph that is harder to scan than a short structured form would be.

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?

For a zero-required-parameter, multi-mode tool this covers the mode-selection logic thoroughly and routes to all three relevant siblings. The remaining shortfalls are the undocumented `topic` parameter and the absence of any indication of what the response contains, which is not covered by an output schema.

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 80 percent, and the description goes further by explaining the combining semantics: video alone packages or critiques an existing upload, idea alone generates for a new topic, both together produce a follow-up grounded in the original, and title/thumbnail_text score pasted assets. The one real gap is the `topic` parameter, which appears in the schema with no description and is never mentioned in the tool description, leaving its difference from `idea` unexplained.

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?

Opens with a specific verb and resource – package a YouTube video, generating titles and thumbnail text or scoring existing ones – and adds a defining constraint that title and thumbnail are treated as one complementary unit. An agent can distinguish this from evaluate_idea, suggest_ideas and find_best_thumbnails without opening any schema.

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?

Gives explicit trigger conditions (help with a title or thumbnail, title options, packaging/re-packaging, review or scoring) and then names the alternatives with the condition that selects each: evaluate_idea for viability, suggest_ideas for brainstorming, find_best_thumbnails for channel-wide thumbnail patterns. It also spells out which parameter combination corresponds to which situation, so routing and invocation are both covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources