Skip to main content
Glama

Render a sound

sound_effect

Renders one sound from the engine's own synth as a stereo WAV, or an ambience of the beds mixed together. Give sound (a name from sound_list) with a, b and c as sound_list says, or give ambience: any of engine, air, surf, rain, drum, gull and creak, each 0 to 1, with seconds (1 to 30, default 10; loop true makes it seamless, its end crossfaded into its start, for a game that plays it on repeat; an ambience otherwise fades out). seed varies a one-shot, rate is 44100 or 48000, and peak_db (-30 to 0, default -3) is where the loudest sample sits, so a footstep and a thunder come back at one level; raw true keeps the synth's own. Nothing is sampled from a recording. Costs 1 unit.

Input Schema

NameRequiredDescriptionDefault
aNoThe sound's first parameter, as sound_list says what it does for this sound.
bNoThe sound's second parameter, 0 to 1, as sound_list says.
cNoThe sound's third parameter, -1 to 1, as sound_list says.
rawNoTrue to keep the synth's own level instead of normalising to peak_db.
loopNoTrue to make an ambience seamless, its end crossfaded into its start.
rateNoSample rate in hertz: 44100 or 48000.
seedNoA whole number that varies a one-shot sound.
soundNoA sound name from sound_list. Give this, or ambience.
peak_dbNoWhere the loudest sample sits in dBFS, -30 to 0 (default -3).
secondsNoLength of an ambience in seconds, 1 to 30 (default 10).
ambienceNoInstead of sound: a mix of beds (engine, air, surf, rain, drum, gull, creak), each a level from 0 to 1.

Output Schema

NameRequiredDescriptionDefault
msNoMilliseconds the run took.
jobYesThe job id; the job tool reads it.
verbNoThe tool that made it.
filesNoFiles made, each with a name, type, size and a signed URL.
unitsNoUnits this call cost.
resultNoThe engine's own answer, a JSON document.
statusNoqueued when the job runs in the background.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • addedInput schema / properties / a / description
      Added value: +"The sound's first parameter, as sound_list says what it does for this sound."
    • addedInput schema / properties / ambience / description
      Added value: +"Instead of sound: a mix of beds (engine, air, surf, rain, drum, gull, creak), each a level from 0 to 1."
    • addedInput schema / properties / b / description
      Added value: +"The sound's second parameter, 0 to 1, as sound_list says."
    • addedInput schema / properties / c / description
      Added value: +"The sound's third parameter, -1 to 1, as sound_list says."
    • addedInput schema / properties / loop / description
      Added value: +"True to make an ambience seamless, its end crossfaded into its start."
    • addedInput schema / properties / peak_db / description
      Added value: +"Where the loudest sample sits in dBFS, -30 to 0 (default -3)."
    • addedInput schema / properties / rate / description
      Added value: +"Sample rate in hertz: 44100 or 48000."
    • addedInput schema / properties / raw / description
      Added value: +"True to keep the synth's own level instead of normalising to peak_db."
    • addedInput schema / properties / seconds / description
      Added value: +"Length of an ambience in seconds, 1 to 30 (default 10)."
    • addedInput schema / properties / seed / description
      Added value: +"A whole number that varies a one-shot sound."
    • addedInput schema / properties / sound / description
      Added value: +"A sound name from sound_list. Give this, or ambience."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": true,
      +  "properties": {
      +    "files": {
      +      "description": "Files made, each with a name, type, size and a signed URL.",
      +      "items": {
      +        "additionalProperties": {},
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "job": {
      +      "description": "The job id; the job tool reads it.",
      +      "type": "string"
      +    },
      +    "ms": {
      +      "description": "Milliseconds the run took.",
      +      "type": "number"
      +    },
      +    "result": {
      +      "description": "The engine's own answer, a JSON document."
      +    },
      +    "status": {
      +      "description": "queued when the job runs in the background.",
      +      "type": "string"
      +    },
      +    "units": {
      +      "description": "Units this call cost.",
      +      "type": "number"
      +    },
      +    "verb": {
      +      "description": "The tool that made it.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "job"
      +  ],
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: cost of 1 unit, stereo WAV output, loop behavior (end crossfaded into start for repeat playback) versus the otherwise fading-out ambience, seed-driven variation of one-shots, and the explicitness that nothing is sampled from a recording. IdempotentHint=false is consistent with the seed discussion.

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?

Purpose and mode selection are front-loaded, and every clause carries information despite the density. The long semicolon-chained sentences mixing mode selection, loop semantics and level semantics make it harder to scan than a bulleted breakdown would be.

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?

An output schema exists, so return format need not be described, and the description covers everything else an agent needs: mode choice, ranges and defaults, cost, determinism, and the no-sampling constraint. Nothing material is missing for an 11-parameter render tool.

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 real meaning: peak_db is framed functionally ('so a footstep and a thunder come back at one level'), raw as keeping the synth's own level, and a/b/c as per-sound parameters read from sound_list. The loop crossfade and default values are also clarified in prose.

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 ('Renders one sound from the engine's own synth as a stereo WAV, or an ambience of the beds mixed together') and immediately names the two mutually exclusive modes. An agent can distinguish this from sound_list (catalog lookup) and voice_speak (speech synthesis) 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?

Explicitly routes between the two modes ('Give sound ... or give ambience: ...') and points to sound_list as the authority for the a/b/c meanings. It gives clear selection context but states no exclusions or prerequisites (e.g., what happens if both sound and ambience are supplied).

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