Neume

change_lyrics

Destructive

Change the words of one part of one of their songs (a part 5–30 seconds long), sung again in the same voice; the rest of the song stays as it is. Makes a new song and keeps the original. Costs 1 credit(s). Call get_song_parts first to find the part, write the new lines with them, and only call this once they agree to the new lines. Hosts that show MCP Apps draw a card that shows its progress and then plays it.

Input Schema

Name	Required	Description
`part`	Yes	The part to change, an id from get_song_parts (e.g. chorus#2)
`lines`	Yes	Every line sung there after the change: the new lines where they change, the old ones word for word where they don't
`songId`	Yes	One of their songs
`to_line`	No	Last line of the part to change (1-based); leave out for the whole part
`from_line`	No	First line of the part to change (1-based); leave out for the whole part
`little_kept_ok`	No	Only after telling them that very little of the song is kept around the part and they chose to go ahead anyway

Output Schema

Name	Required	Description	Default
`status`	Yes
`message`	Yes
`songIds`	Yes
`estimatedTime`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 10, 2026

addedInput schema / properties / little_kept_ok

Added value: +{
+  "description": "Only after telling them that very little of the song is kept around the part and they chose to go ahead anyway",
+  "type": "boolean"
+}

First observedOct 9, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true, readOnlyHint=false, but the description adds material context beyond them: it costs 1 credit, it creates a new song while keeping the original, the part is re-sung in the same voice, and MCP App hosts render a progress card that then plays the result. It also fronts the get_song_parts prerequisite and the user-consent gate.

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?

Two long sentences that are front-loaded with the core action and then the workflow and side effects; almost every clause carries distinct information (scope, duration, credit cost, consent gate, UI behavior). Slightly dense, but nothing is padding.

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?

An output schema exists, so return values need not be explained. The description covers cost, side effects, prerequisites, and host UI, which is sufficient for a 6-parameter mutation tool. It omits that from_line/to_line allow changing only a sub-range of a part rather than the whole part, a minor but real gap.

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 description coverage is 100%, so all six parameters including from_line/to_line and the consent flag little_kept_ok are already documented in the schema. The description adds the workflow hint that 'part' comes from get_song_parts and the 5–30 second duration bound, but no syntax or format detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource ('Change the words of one part of one of their songs') plus the scope constraint (a part 5–30 seconds long, same voice) and what is preserved (rest of the song stays as it is). An agent can distinguish this from generate_remix or reimagine_song 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 Guidelines4/5

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

Gives an explicit ordered workflow: call get_song_parts first to find the part, write the new lines with the user, and only invoke once they agree. It does not name the sibling alternatives (reimagine_song, generate_remix) or say when changing lyrics is the wrong choice, so it stops short of full when/when-not guidance.

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

All Neume tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?