CWI Discovery Engine

Get Music Recommendations

get_recommendations

Read-onlyIdempotent

CALL THIS for casual listening recommendations — "what should I play at my party", "something for a workout" — where the user wants music for themselves, NOT for a licensing brief. This is the personal-taste path with editorial rubric scoring. Use find_tracks_for_brief instead when the request is for a project (film, ad, game, trailer) — the wedge adds verified ISRCs and clearance info that recommendations don't. Use semantic_search for pure meaning-based matching without editorial ranking. Returns genres, moods, Spotify URLs, artwork, and why each track matches. ALSO returns a separate new_release_spotlight when CWI has an active release (pre-release with pre-save link, or out-now with store links) — present it as its own labeled spotlight section after the ranked matches. Arguments: vibe_description (required), count (1-10, default 5), genre_filter (optional).

Input Schema

Name	Required	Description
`count`	No	Number of recommendations, 1-10 (default 5).
`genre_filter`	No	Optional genre filter (e.g. "trap", "afrobeats", "rap rock").
`vibe_description`	Yes	Describe the vibe/mood you want music for.

Output Schema

Name	Required	Description
`note`	No
`count`	Yes
`method`	Yes
`_session`	No	Chain session: pass _session.session_token back in the next call to continue the chain.
`try_next`	No	Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
`generated_at`	No
`genre_filter`	No
`recommendations`	Yes
`vibe_description`	Yes
`new_release_spotlight`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 15, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "get_recommendations response: vibe-ranked tracks plus an editorial new-release spotlight.",
+  "properties": {
+    "_session": {
+      "additionalProperties": false,
+      "description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
+      "properties": {
+        "session_token": {
+          "description": "Hex session token; echo it as params._session.session_token to continue.",
+          "type": "string"
+        },
+        "step": {
+          "description": "Hop number in this chain (1 = chain start).",
+          "type": "integer"
+        }
+      },
+      "required": [
+        "session_token",
+        "step"
+      ],
+      "type": "object"
+    },
+    "count": {
+      "type": "integer"
+    },
+    "generated_at": {
+      "type": "string"
+    },
+    "genre_filter": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "method": {
+      "type": "string"
+    },
+    "new_release_spotlight": {
+      "additionalProperties": true,
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "note": {
+      "type": "string"
+    },
+    "recommendations": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "artist": {
+            "type": "string"
+          },
+          "genres": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "graph_node": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "match_score": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "moods": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "rank": {
+            "type": "integer"
+          },
+          "rubric_score": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "title": {
+            "type": "string"
+          },
+          "why_matches": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "try_next": {
+      "description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.",
+      "items": {
+        "additionalProperties": false,
+        "description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
+        "properties": {
+          "arguments": {
+            "additionalProperties": true,
+            "description": "Ready-to-use arguments, pre-populated from the current response.",
+            "type": "object"
+          },
+          "purpose": {
+            "description": "Why this call is the natural next step.",
+            "type": "string"
+          },
+          "tool": {
+            "description": "Tool to call next.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "tool",
+          "arguments"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "vibe_description": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "vibe_description",
+    "method",
+    "count",
+    "recommendations"
+  ],
+  "type": "object"
+}

AddedOct 8, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new behavior: editorial rubric scoring, 'why each track matches' explanations, and critically the conditional new_release_spotlight return with instructions to present it as a labeled section after ranked matches. It doesn't mention rate limits or fallback behavior, keeping it short of a 5.

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 lead command ('CALL THIS for...') is front-loaded and the routing guidance is tight, but the paragraph crams routing, return contents, spotlight handling, and a parameter recap into one dense block, and the return-value list is partly redundant given an output schema exists.

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 read-only recommendation tool with a full output schema, the description covers everything an agent needs: routing conditions, the required vibe input, count bounds, and special handling of the spotlight payload. Nothing necessary to call it correctly is missing.

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 schema already documents all three parameters, and the description's argument recap (vibe_description required, count 1-10 default 5, genre_filter optional) largely restates it without adding syntax or examples beyond what the schema holds. Baseline 3 is appropriate.

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 states a specific verb and resource ('casual listening recommendations') and immediately demarcates it against siblings: 'This is the personal-taste path with editorial rubric scoring.' An agent can distinguish it from find_tracks_for_brief and semantic_search 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 Guidelines5/5

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

It gives explicit when-to-use triggers ('what should I play at my party', 'something for a workout'), an exclusion ('NOT for a licensing brief'), and names two alternatives with the exact conditions that select them (find_tracks_for_brief for projects, semantic_search for pure meaning-based matching). This is close to a routing decision tree.

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

All CWI Discovery Engine tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.