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

spotify-discovery-mcp

by wkbaran
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Start a lane run

discovery_begin

Starts a discovery lane run: finds or creates today's playlist, collects new releases from known labels and artists, filters already-recommended tracks, and returns new and carried-over picks.

Instructions

Step 1 of a lane run. Finds or creates today's playlist, fetches new releases from the lane's known labels and artists, drops anything already recommended, and returns the lane brief plus a list with refs: K (new from known sources) and C (carried over). Call once per run. With feed: false it skips the known labels and artists (and the pending web finds) for now; discovery_fill checks them later, only for as many picks as the run is short.

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_begin"
  }
}

Input Schema

NameRequiredDescriptionDefault
feedNofalse: check the known labels and artists later, with discovery_fill, only if the web finds fall short.
laneYesThe lane id from lanes.json, e.g. "a-dnb".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare the safety profile (not read-only, not idempotent, open-world, non-destructive), and the description is consistent with all of them: it openly states it creates a playlist, reaches out to external release sources, and mutates recommendation state by dropping already-recommended tracks. The "call once per run" instruction usefully reinforces the non-idempotent hint. It stops short of describing failure modes or what happens if a playlist already exists from an earlier run.

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?

Front-loaded with the workflow position, then the effects, then the return shape, then the feed: false exception — a logical order with no filler. The final sentence is dense (it packs the deferral, the sibling handoff, and the quantity condition), but every clause carries information.

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 correctly compensates by explaining the return value (lane brief plus a list with refs K for new-from-known and C for carried over). Combined with annotations and full schema coverage, an agent has nearly everything needed; only error/edge-case behavior is absent.

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 both parameters are already documented, but the description still adds real meaning: feed: false is explained as deferring known labels/artists AND pending web finds to discovery_fill, with the condition "only for as many picks as the run is short." That is substantive semantics beyond the schema's default-true note.

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 names a concrete workflow role ("Step 1 of a lane run") and enumerates the actual operations: finds or creates today's playlist, fetches new releases from known labels and artists, filters already-recommended items, and returns a lane brief with K/C refs. That is specific enough that an agent can distinguish it from discovery_fill or discovery_review without opening a schema.

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?

It gives an explicit invocation rule ("Call once per run") and routes the deferred branch to the correct sibling: with feed: false, discovery_fill handles known labels and artists later, "only for as many picks as the run is short." What's missing is guidance on the other siblings (discovery_status, discovery_review, discovery_finish) — an agent must infer the rest of the chain from tool names.

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