CWI Discovery Engine

Search Catalog

search_catalog

Read-onlyIdempotent

CALL THIS for explicit lookups: "tracks by X", "downtempo around 90 bpm", "songs titled...". Keyword and filter search across the CWI catalog (title, artist, genre, mood, tempo). Use semantic_search instead if the user describes a feeling. Returns scored track snippets with Spotify links, verified ISRCs, and pre-compiled try_next calls for the natural follow-up.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "q": "<q>"
    },
    "name": "search_catalog"
  }
}

Input Schema

Name	Required	Description	Default
`q`	Yes	Search keywords, e.g. "cyberpunk rap" or "dark cinematic". Truncated at 500 characters.
`limit`	No	Max tracks to return, 1-10 (default 5).

Output Schema

Name	Required	Description
`count`	Yes
`limit`	No
`query`	Yes
`tokens`	No
`results`	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
`new_release_spotlight`	No	Active pre-release spotlight: title, artist, drop date, presave URL, ISRC.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 15, 2026

addedOutput schema / properties / new_release_spotlight

Added value: +{
+  "additionalProperties": true,
+  "description": "Active pre-release spotlight: title, artist, drop date, presave URL, ISRC.",
+  "type": "object"
+}

Changed1 schema field changedOct 15, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "search_catalog response: scored track snippets plus pre-compiled try_next calls.",
+  "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"
+    },
+    "limit": {
+      "type": "integer"
+    },
+    "query": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": true,
+        "description": "Track snippet (list views carry a snippet, not the full prose description).",
+        "properties": {
+          "artist": {
+            "type": "string"
+          },
+          "featured": {
+            "type": "boolean"
+          },
+          "genres": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "graph_node": {
+            "description": "Knowledge-graph node id, e.g. track:cyberpunk-2027.",
+            "type": "string"
+          },
+          "moods": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "title": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "tokens": {
+      "items": {
+        "type": "string"
+      },
+      "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"
+    }
+  },
+  "required": [
+    "query",
+    "count",
+    "results"
+  ],
+  "type": "object"
+}

Changed1 schema field changedOct 8, 2026

addedInput schema / properties / limit

Added value: +{
+  "description": "Max tracks to return, 1-10 (default 5).",
+  "type": "number"
+}

First observedOct 5, 2026

TDQS

A4.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is fully covered. The description adds return-content detail (scored snippets, Spotify links, verified ISRCs, try_next calls), but since an output schema exists that content is largely redundant and no auth, rate-limit, or truncation behavior is disclosed. Adequate but adds limited behavioral value beyond structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the imperative ("CALL THIS") with concrete query examples, then the scope, then the alternative, then the return shape. Dense but every clause earns its place with no 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?

With an output schema present, return values need not be spelled out, and the description already covers scope, usage triggers, the sibling alternative, and follow-up behavior. Nothing an agent needs to call this correctly 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 beyond the schema by listing the fields q matches against (title, artist, genre, mood, tempo) and showing a tempo-style query example. This clarifies what a query string can target, adding real meaning over the generic schema 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 (keyword and filter search) and resource (CWI catalog) and enumerates the searchable dimensions (title, artist, genre, mood, tempo). It explicitly distinguishes itself from the sibling semantic_search, so an agent can route without opening either 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?

Gives explicit when-to-use triggers ("tracks by X", "downtempo around 90 bpm", "songs titled...") and an explicit alternative with its own trigger ("Use semantic_search instead if the user describes a feeling"). Nothing is left to inference.

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

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.