Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Recut recording

recut_recording
Idempotent

Create new clips from an existing recording using a different topic or focus instruction while keeping current clips and posts intact.

Instructions

Cuts a fresh set of clips from a recording following a new instruction, such as different topics or focus. Existing clips and their posts are kept. Counts against the account's edited-clip allowance.

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": {
      "recording_id": "<recording_id>",
      "instruction": "<instruction>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "recut_recording"
  }
}

Input Schema

NameRequiredDescriptionDefault
account_idNo
instructionYes
recording_idYesThe recording's id, from list_recordings.
idempotency_keyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations, the description discloses two behaviors an agent could not infer: existing clips and their posts survive the operation, and the call consumes the account's edited-clip allowance. What it omits is whether the recut runs asynchronously and how progress is tracked, which matters given openWorldHint=true and the presence of wait_for_recording.

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?

Three short sentences, each carrying distinct information: what it does, what it preserves, what it costs. The key differentiator (new instruction) is front-loaded and there is no filler.

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

Completeness3/5

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

For a mutating, quota-consuming tool with no output schema and a required idempotency key, the definition covers purpose and side effects but not what the call returns or how to follow up on a long-running recut. It is adequate to decide whether to call it, less so to invoke and handle it correctly.

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

Parameters3/5

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

Schema coverage is only 25%, with recording_id and account_id documented but instruction and idempotency_key bare. The description gives the instruction parameter real meaning ('different topics or focus') and clarifies its intent, but it says nothing about the required idempotency_key or its retry semantics, so the coverage gap is only partly closed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('Cuts a fresh set of clips') and resource ('from a recording') plus the distinguishing condition ('following a new instruction, such as different topics or focus'), which separates it from a plain re-run or clip-design change. It does not name a sibling tool it should be preferred over, so it stops short of a 5.

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 phrase 'following a new instruction, such as different topics or focus' implies the situation that calls for this tool, and 'Existing clips and their posts are kept' signals it is additive rather than a replacement. However, it never states when NOT to use it or which sibling (e.g. retry_recording, change_clip_design) to pick instead, leaving routing to inference.

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

Deploy Server

Other Tools