Skip to main content
Glama
Sign In

CWI Discovery Engine

by io.github.CumulativeWebInc
OverviewDiscussionsAdmin

Get Videos

get_videos
Read-onlyIdempotent

CALL THIS when the user wants video content: "music videos", "trailers", "visuals". Returns videos with YouTube links and embed URLs.

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": "get_videos"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoOptional: filter by type (trailer, music-video, visualizer, live).
artistNoOptional: filter by artist name.

Output Schema

NameRequiredDescriptionDefault
okYes
countYes
videosYes
_sessionNoChain session: pass _session.session_token back in the next call to continue the chain.
try_nextNoSuggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "get_videos response: videos with YouTube links and embed URLs.",
+  "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"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "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"
+    },
+    "videos": {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "ok",
+    "videos",
+    "count"
+  ],
+  "type": "object"
+}
  2. Added

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety and repeatability are covered. The description adds the payload shape (links and embed URLs), but that overlaps with the existing output schema and says nothing about filtering behavior or result limits.

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?

Two sentences, zero filler, and the invocation condition is front-loaded before the return payload. Every clause carries information an agent can act on.

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?

With an output schema present, the description need not explain returns, yet it does anyway without harm. For a two-optional-parameter read tool with full annotation and schema coverage, nothing essential is missing, though a note on filter interaction would round it out.

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% — both optional filters (type, artist) are documented in the schema itself with example values. The description adds no syntax, matching rules, or guidance on combining the filters, so baseline 3 applies.

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?

States a clear resource (videos) and even the payload (YouTube links and embed URLs), so the agent knows what it gets back. However, it leans on trigger phrases rather than a crisp verb+resource statement, and gives no explicit contrast with siblings like get_track or semantic_search, though no sibling covers video content.

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?

"CALL THIS when the user wants video content" supplies a concrete activation condition reinforced by example utterances (music videos, trailers, visuals). It stops short of naming alternatives or a when-not condition, so an agent must infer that non-video media requests route elsewhere.

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 toolsInspect
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