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

spotify-discovery-mcp

by wkbaran
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Fill a lane run from known sources

discovery_fill
Idempotent

Submit chosen web finds for a genre lane to let the server check known labels and artists on Spotify and return new candidate refs for available slots.

Instructions

For a run begun with feed: false, after choosing from the web finds. Give the picks so far; the server works out how many more the lane has room for, checks the known labels and artists (then earlier web finds now on Spotify) for about that many, and lists the new K and C refs. Once per run.

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_fill"
  }
}

Input Schema

NameRequiredDescriptionDefault
laneYesThe lane id from lanes.json, e.g. "a-dnb".
picksNoThe refs chosen so far, e.g. ["W2", "W5"].

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish that this is non-read-only, open-world, idempotent, and non-destructive, so the bar is lower, but the description still adds real context: it performs external label/artist lookups (including earlier web finds now on Spotify), delegates capacity math to the server, and should be called once per run. It does not describe failure behavior when the lane is already full or the lookup misses.

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

Conciseness3/5

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

The precondition is front-loaded, which is good, but the body is a single dense semicolon chain mixing input, server behavior, and output. Every clause carries information, yet the run-on phrasing and unexplained shorthand make it slower to parse than it needs to be.

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 does carry the return burden and discharges it by stating that new K and C refs are listed. For a two-parameter, server-computed mutation in an open-world discovery workflow, that is nearly sufficient; only error and idempotency edge cases are 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 coverage is 100% and both parameters are documented there, including the lane id source and the maxItems-30 picks array, so the baseline is 3. The description restates picks as 'the picks so far' and hints that their count drives how many more the lane has room for, but adds no formatting or edge-case meaning beyond the schema.

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 commits to a specific action: take the picks so far, have the server compute remaining lane capacity, check known labels/artists, and return new K and C refs. It differentiates itself from siblings by tying itself to a run begun with feed: false and to the web-find step. It stops short of 5 because the outcome vocabulary ('K and C refs', 'web finds') is never defined, so an agent must infer what the produced refs are.

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?

Preconditions are explicit: only for a run started with feed: false, and only after choosing among the web finds, which implicitly places it after discovery_review. The 'Once per run' clause gives a frequency constraint. It lacks an explicit when-not statement or a named alternative, so it is strong context rather than full routing guidance.

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