Skip to main content
Glama

replace_section

Idempotent

COSTS CREDITS (see list_song_tools): state the price and get the user's confirmation first. Re-generate one section of a song with new lyrics, keeping the rest. Only for Rao/Suno songs and uploaded songs. The section must be 10-60 seconds and at most half the song. Returns an id; poll get_generation.

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": {
      "id": "<id>",
      "start": "<start>",
      "end": "<end>",
      "lyrics": "<lyrics>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "replace_section"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesSource song id (songs[].id from get_generation / list_songs / save_upload).
endYesSection end in seconds.
startYesSection start in seconds (get_timed_lyrics helps find it).
styleNo
titleNo
lyricsYesReplacement lyrics for that section.
versionNoRao/Suno version id (list_song_tools.recreate.versions); omit for the default. Sets the price.
idempotencyKeyYes8-64 chars [A-Za-z0-9._:-]. Same rules as generate_music: stable per logical request, resend the same key + params after a timeout instead of paying twice; new key when anything changes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

The annotations only declare openWorldHint, idempotentHint, and destructiveHint=false, so the description carries real weight: it discloses the credit cost, the 10-60 second and half-the-song constraints, and that the result is asynchronous (returns an id). It does not say whether the source song is modified in place or a new song is produced, which is the main remaining behavioral ambiguity.

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 tight sentences with the highest-stakes information (cost and confirmation) front-loaded, followed by scope and follow-up. No sentence is filler.

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 correctly explains the return value and the polling step, and it covers the critical constraints for an 8-parameter, 5-required mutation-style tool. The only gap is the unspecified effect on the original song and the undocumented style/title parameters.

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 75%, so the schema already documents most fields; the description adds meaning beyond it by tying start/end to the 10-60 second and at-most-half-length rules and by implying which songs are valid for id. It says nothing about the undocumented style and title parameters.

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 gives a specific verb and resource ("Re-generate one section of a song with new lyrics, keeping the rest") and immediately bounds the scope with size limits, so an agent can distinguish it from whole-song siblings such as restyle_song or extend_song.

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 states upfront that the call COSTS CREDITS and requires quoting the price and getting user confirmation, restricts applicability to Rao/Suno and uploaded songs, and tells the agent to poll get_generation afterward — a full when-to-use, precondition, and follow-up chain.

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.