Moose Tracker

Plan, check and analyze a song

song

Read-onlyIdempotent

Plans and analyzes a song (render checks too); returns a share link that plays it in the browser (90 days, no render). Stages: plan, write, light analysis loop, one deep analysis, fix; then the share link to listen, or one render to embed. analyze:true: light; deep:true: measured. Schema eb59845f.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "song"
  }
}

Input Schema

Name	Required	Description
`len`	No	Target seconds
`mtl`	No	Song in MTL text (describe topic=mtl). Kept 2 hours as a working copy: later calls can send ref (the songId) instead.
`ref`	No	Instead of mtl: a songId from an earlier reply (kept 2 hours), a render asset id, or a share link
`alts`	No	Other MTL versions to rank by score
`deep`	No	With analyze: deep analysis, a measured analysis-only render. Suited to once or twice when the song is nearly done
`loop`	No	Should loop
`plan`	No	Alone: {bpm, meter, key, peak, sections:[{id, bars, energy 1-5, role}], mix?} gives a skeleton, timing, checks
`check`	No	Same as analyze
`genre`	No	Genre or alias, see describe(topic="genres")
`range`	No	With analyze: one section, e.g. "2" or "2-3" (order entries)
`style`	No	Voice palette; default chip
`energy`	No	Planned 1-5 per order entry, for check:true
`intent`	No	Deliberate choices, not scored
`layers`	No	With mtl: batch edits {add:["A: 3 i3 v40: C4 . . ."], replace, remove:["A:3"], instruments, mix, notes}; returns the edited song
`return`	No	mtl echoes the song back
`voices`	No	List these instruments' settings
`analyze`	No	Light analysis: no audio, instant, free. Suited to every edit
`compare`	No	With analyze: A/B against an earlier songId, asset id or share link
`compose`	No	Instead of mtl: {bpm, form, chords, parts:[{id,gen}]}. describe(topic="generators")

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedNov 10, 2026

changedInput schema / description

Previous value: -"Schema 3b8fe45c"New value: +"Schema eb59845f"

addedInput schema / properties / analyze

Added value: +{
+  "description": "Light analysis: no audio, instant, free. Suited to every edit",
+  "type": "boolean"
+}

changedInput schema / properties / check / description

Previous value: -"Score only: no summary, no render, free"New value: +"Same as analyze"

addedInput schema / properties / compare

Added value: +{
+  "description": "With analyze: A/B against an earlier songId, asset id or share link",
+  "type": "string"
+}

addedInput schema / properties / deep

Added value: +{
+  "description": "With analyze: deep analysis, a measured analysis-only render. Suited to once or twice when the song is nearly done",
+  "type": "boolean"
+}

changedInput schema / properties / layers / description

Previous value: -"With mtl: batch edits {add:[\"A: 3 i3 v40: C4 . . .\"], replace, remove:[\"A:3\"], instruments, mix}; returns the edited song"New value: +"With mtl: batch edits {add:[\"A: 3 i3 v40: C4 . . .\"], replace, remove:[\"A:3\"], instruments, mix, notes}; returns the edited song"

addedInput schema / properties / layers / properties / notes

Added value: +{
+  "description": "Polyphony: [{ch, ins, section?, notes:[[pitch, startBeat, beats, vel]]}]; placed on sub-channels",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "ch": {
+        "type": "integer"
+      },
+      "ins": {
+        "type": [
+          "integer",
+          "string"
+        ]
+      },
+      "notes": {
+        "items": {},
+        "type": "array"
+      },
+      "section": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "ch",
+      "ins",
+      "notes"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedInput schema / properties / mtl / description

Previous value: -"Song in MTL text (describe topic=mtl). Send it whole each time; we keep none."New value: +"Song in MTL text (describe topic=mtl). Kept 2 hours as a working copy: later calls can send ref (the songId) instead."

addedInput schema / properties / range

Added value: +{
+  "description": "With analyze: one section, e.g. \"2\" or \"2-3\" (order entries)",
+  "type": "string"
+}

addedInput schema / properties / ref

Added value: +{
+  "description": "Instead of mtl: a songId from an earlier reply (kept 2 hours), a render asset id, or a share link",
+  "type": "string"
+}

Changed1 schema field changedNov 10, 2026
- changedInput schema / description
```
Previous value: -"Schema 9b20e675"New value: +"Schema 3b8fe45c"
```

Changed4 schema fields changedNov 9, 2026

changedInput schema / description

Previous value: -"Schema 415a8741"New value: +"Schema 9b20e675"

addedInput schema / properties / energy

Added value: +{
+  "description": "Planned 1-5 per order entry, for check:true",
+  "items": {
+    "type": "number"
+  },
+  "type": "array"
+}

addedInput schema / properties / layers

Added value: +{
+  "additionalProperties": false,
+  "description": "With mtl: batch edits {add:[\"A: 3 i3 v40: C4 . . .\"], replace, remove:[\"A:3\"], instruments, mix}; returns the edited song",
+  "properties": {
+    "add": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "instruments": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "mix": {
+      "additionalProperties": false,
+      "description": "dB; \"-inf\" silences, 0 resets. Faders balance (first choice), gain sets one sound, level is overall loudness",
+      "properties": {
+        "faders": {
+          "additionalProperties": {
+            "anyOf": [
+              {
+                "maximum": 6,
+                "minimum": -60,
+                "type": "number"
+              },
+              {
+                "enum": [
+                  "-inf",
+                  "off"
+                ],
+                "type": "string"
+              }
+            ],
+            "default": 0
+          },
+          "description": "{\"2\": -6}",
+          "propertyNames": {
+            "pattern": "^([1-9]|1[0-6])$"
+          },
+          "type": "object"
+        },
+        "gain": {
+          "additionalProperties": {
+            "anyOf": [
+              {
+                "maximum": 12,
+                "minimum": -60,
+                "type": "number"
+              },
+              {
+                "enum": [
+                  "-inf",
+                  "off"
+                ],
+                "type": "string"
+              }
+            ],
+            "default": 0
+          },
+          "description": "{\"i3\": -3}",
+          "propertyNames": {
+            "pattern": "^i?\\d{1,2}$"
+          },
+          "type": "object"
+        },
+        "level": {
+          "anyOf": [
+            {
+              "maximum": 6,
+              "minimum": -60,
+              "type": "number"
+            },
+            {
+              "enum": [
+                "-inf",
+                "off"
+              ],
+              "type": "string"
+            }
+          ],
+          "default": 0
+        }
+      },
+      "type": "object"
+    },
+    "remove": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "replace": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

addedInput schema / properties / plan

Added value: +{
+  "additionalProperties": true,
+  "description": "Alone: {bpm, meter, key, peak, sections:[{id, bars, energy 1-5, role}], mix?} gives a skeleton, timing, checks",
+  "type": "object"
+}

Changed3 schema fields changedNov 9, 2026

changedInput schema / description

Previous value: -"Schema d568427c"New value: +"Schema 415a8741"

addedInput schema / properties / intent

Added value: +{
+  "additionalProperties": false,
+  "description": "Deliberate choices, not scored",
+  "properties": {
+    "fixed": {
+      "items": {
+        "enum": [
+          "tempo",
+          "swing",
+          "meter",
+          "length",
+          "form",
+          "loop"
+        ],
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "loop": {
+      "type": "boolean"
+    },
+    "unpitched": {
+      "description": "Drum tracks",
+      "items": {
+        "minimum": 1,
+        "type": "integer"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

addedInput schema / properties / voices

Added value: +{
+  "description": "List these instruments' settings",
+  "items": {
+    "maximum": 99,
+    "minimum": 1,
+    "type": "integer"
+  },
+  "maxItems": 16,
+  "type": "array"
+}

Changed1 schema field changedNov 4, 2026
- changedInput schema / description
```
Previous value: -"Schema 90ddc268"New value: +"Schema d568427c"
```
Changed1 schema field changedNov 3, 2026
- addedInput schema / description
```
Added value: +"Schema 90ddc268"
```
First observedOct 30, 2026

TDQS

B3.1/5.0

Behavior1/5

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

The annotations declare readOnlyHint=true and destructiveHint=false, but the description describes a write/fix workflow, layer batch edits that return the edited song, and one render to embed. That directly contradicts the read-only annotation, so the description cannot be treated as behaviorally consistent even though it contains useful details like the 90-day share link and 2-hour working copy.

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?

The description is short and front-loads the overall purpose before listing stages and flags, which is appropriate for a complex tool. It is somewhat cryptic and includes the unhelpful opaque token 'Schema eb59845f', but it contains little outright 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?

For a complex 19-parameter tool with nested objects and no output schema, the description covers the major workflow stages, analysis modes, share-link lifetime, andrender outcome. The input schema carries detailed parameter documentation, so most remaining gaps are about error conditions and permission behavior rather than core calling semantics.

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 the baseline is 3, and the description adds only limited meaning beyond the schema. It restates analyze/deep behavior and mode interactions, but it does not add much syntax or constraint detail for the 19 parameters beyond what the schema already documents.

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 names specific verbs and a resource: plans, analyzes, writes, checks, and fixes a song, and it describes the share-link and render outcomes. It distinguishes some sibling behavior indirectly by referencing describe(topic=...) and by saying the share link involves no render, but the broad multi-mode scope makes the tool less crisply differentiated from render and feedback.

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?

It gives in-tool mode guidance such as analyze:true for light analysis, deep:true for measured analysis, and plan alone for a skeleton. However, it does not explicitly say when to choose this tool over render, assets, convert, or feedback, and the exclusions are only implied by the render/no-render wording.

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

All Moose Tracker 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?