Skip to main content
Glama

Suggest shorts from a long video

suggest_shorts

Picks the best moments of a long-form project as 9:16 shorts: one continuous stretch each, 15 to 56.8 s of speech, opening on a hook, with a hook title, scores, the reason and short-ad checks. Accepted shorts are kept; the rest are replaced. One model call through AI Gateway, 2 credits: use estimate_only first and tell the person the price.

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": {
      "project_id": "<project_id>",
      "count": "<count>"
    },
    "name": "suggest_shorts"
  }
}

Input Schema

NameRequiredDescriptionDefault
countYesHow many shorts, 1 to 10. About one per 2 minutes of finished video.
modelNoGateway model id; the default is the cheapest that passed the eval
project_idYesFrom create_project
estimate_onlyNoPrice it without spending; tell the person the price first

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only say it's non-read-only and open-world; the description adds the substantive facts: one model call via AI Gateway, a cost of 2 credits, and the replacement semantics ('Accepted shorts are kept; the rest are replaced'). It does not describe failure behavior or the response shape, keeping it below a 5.

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?

Front-loaded with the purpose, then a compact colon list of output characteristics, then the cost warning. Every clause carries information an agent needs; nothing is restated from the schema or annotations.

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?

With no output schema, the description shoulders return-value explanation and does so by listing what each short contains (hook title, scores, reason, short-ad checks). Cost and estimate workflow are covered; only error and partial-success behavior are unaddressed.

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 baseline is 3, but the description adds meaning beyond the schema by tying estimate_only to the pricing workflow and framing the result as a paid model call. It also reinforces output constraints (15 to 56.8 s, hook opening) that give context to the count parameter.

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: 'Picks the best moments of a long-form project as 9:16 shorts.' The output type (9:16 shorts), the source (long-form project), and the selection behavior (best moments) are all stated, which separates it from sibling suggest_* tools that produce graphics or regions.

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

Usage Guidelines4/5

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

Gives an explicit operational sequence: 'use estimate_only first and tell the person the price,' which is real when-to-use guidance for a paid call. It stops short of naming alternative tools for other suggestion types, so an agent must infer routing from resource names alone.

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