Sound Vocabulary

Make a sound effect from a description

make_sound

Read-onlyIdempotent

Use this when someone needs a UI, game or motion-design sound effect: a click, a notification ding, a whoosh, a coin pickup, a riser or a logo sting. Pass the person's own words as describe ('a short soft click for a toggle', 'deep whoosh for a scene cut'), one call per sound, or an id from list_sounds. Words such as high, deep, short, long, bright or muffled tweak the sound; pitch, length and brightness set it exactly. Returns the best match named by the Universal Category System (UCS), a WAV link, a Web Audio function named after the sound, such as playCoinPickup(), that plays the same sound (give code exactly as returned; several sounds can share one script), a UCS file name and close alternatives. Everything is CC0. status no_match lists the categories to rephrase with.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "describe": "a short soft click for a toggle"
    },
    "name": "make_sound"
  }
}

Input Schema

Name	Required	Description
`id`	No	An id from list_sounds or an earlier answer, instead of describe
`pitch`	No	Pitch shift in semitones; overrides words such as 'high' or 'deep'
`length`	No	Length factor: 0.5 is half as long, 2 is twice as long
`describe`	No	The sound in plain words, such as 'a short soft click for a toggle' or 'deep whoosh for a scene cut'
`brightness`	No	Brightness factor for the filters: below 1 is darker, above 1 is brighter

Output Schema

Name	Required	Description
`sound`	Yes
`source`	Yes
`status`	Yes
`license`	Yes	The license of the sound, the WAV and the code
`describe`	Yes	The description that was matched; null when an id was passed
`categories`	No	On no_match: the UCS categories the vocabulary covers, to rephrase with
`tweak_words`	Yes	Words of the description that changed pitch, length or brightness
`alternatives`	Yes	Close matches to offer next
`matched_words`	Yes	Words of the description that chose the sound

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds substantial behavioral context: the CC0 licensing, the no_match status with category rephrasing guidance, and the instruction to paste the returned Web Audio function verbatim since multiple sounds can share one script. That last point is a real usage hazard disclosed up front.

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?

Front-loaded with the use case, then examples, then the parameter distinction, then returns — a sensible ordering. The returns sentence is dense and partly duplicates the output schema, but no sentence is filler.

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

Completeness5/5

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

For a generation tool with an optional-only parameter set (0 required), the description covers both entry modes (describe vs. id), the tuning precedence, the failure mode, and licensing. Nothing an agent needs in order to call this correctly or interpret a failure is missing.

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 the baseline is 3, but the description goes further by explaining the precedence relationship between describe and the numeric params ('words such as high, deep, short... tweak the sound; pitch, length and brightness set it exactly'). It also shows natural-language describe phrasing that the schema only hints at via one example.

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+resource ('Make a sound effect from a description') and immediately grounds it with concrete artifact types (click, notification ding, whoosh, coin pickup, riser, logo sting). This is clearly distinguishable from the sibling list_sounds, which is referenced only as an id source.

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 a clear triggering condition ('Use this when someone needs a UI, game or motion-design sound effect') and rules out a common confusion by specifying 'one call per sound' and offering the id path via list_sounds. It stops short of explicit when-not-to-use guidance, e.g. it never says to prefer list_sounds when the user just wants to browse.

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

All Sound Vocabulary 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.