Skip to main content
Glama
Sign In
spotify-discovery-mcp

spotify-discovery-mcp

by wkbaran
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Review a lane run's candidates

discovery_review
Idempotent

Lists all tracks available to pick for a genre lane in the current run, including verified web finds, known-source tracks, and pick limits, so you can choose before finishing.

Instructions

Step 3, after the research: lists everything you can pick in the current run, from the server's own copy. Verified web finds (W refs) with their reasons, then the known-source tracks (K and C refs), and the pick limits. Call it once, then discovery_finish, which requires it.

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": {
      "lane": "<lane>"
    },
    "name": "discovery_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
laneYesThe lane id from lanes.json, e.g. "a-dnb".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.0

TDQS

A3.6/5.0
Behavior3/5

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

The description frames the call as a listing (read-like) and says to call it only once, but the annotations declare readOnlyHint=false, implying the call has a write side effect such as marking the run as reviewed; that effect is never explained. It does disclose a useful behavioral constraint (call once, prerequisite for discovery_finish), which the annotations do not convey. Not a direct contradiction, but the unexplained gap between "lists" and readOnlyHint=false costs it.

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 three tight sentences with the workflow position front-loaded and no filler. The density of unexplained shorthand (W/K/C refs, lanes.json) slightly widens the audience the text assumes.

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 no output schema, the description usefully previews the return contents (verified web finds with reasons, then known-source tracks, then pick limits), which is the key thing an agent needs. The remaining gap is the unstated side effect implied by readOnlyHint=false.

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?

The single `lane` parameter is documented in the schema at 100% coverage, including a concrete example format. The description adds no meaning beyond the schema for the parameter, so the 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?

The description gives a specific verb and resource ("lists everything you can pick in the current run") and pins the source ("the server's own copy"), so it is clearly not the same as discovery_fill or verify_tracks. It is not quite a 5 because the payload is described only in jargon ("W refs", "K and C refs") that an agent must already know from elsewhere.

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?

"Step 3, after the research" places the tool in the workflow, and "Call it once, then discovery_finish, which requires it" both prohibits repeated calls and names the next tool. There is no explicit statement of when the tool should be skipped or what to do if the run is not ready, so it falls short of full when/when-not coverage.

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

Deploy Server

Other Tools