Create playlist draft

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

Annotations cover mutation and open-world behavior, but the description adds the operational detail they cannot: ~15s synchronous return with background continuation and a "building" status, the polling cadence, the guarantee that nothing is published until create_playlist, and the full defaults block (5/3/2 tiers, 250 max tracks, interleave, private). It even flags a cost (skipCovers = one Deezer lookup per track).

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

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

Front-loaded with purpose and usage, and almost every clause carries information an agent needs. The cost is that it is one dense ~250-word block mixing seed types, free-text handling, constraints, async behavior, and defaults, which makes targeted re-reading harder than a lightly segmented version.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 27-param, no-required, nested-schema tool with no output schema, the description covers the workflow, async/polling contract, publishing gate, and defaults that an agent needs to invoke it correctly. Remaining gaps are minor (error/unresolved-artist handling is delegated to stopIfUnresolved in the schema) and acceptable given schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

At 70% schema coverage the description meaningfully supplements the schema by enumerating the constraint knobs (tracksPerArtist, maxDurationMin, excludeExplicit, yearRange, bpmRange, skipCovers, excludeTracksFrom) and explaining seed semantics that the schema only hints at (limit as songs-per-seed-song, excludeSeedArtists for "other artists only"). It does not touch several params (days, order, sources, discoveryOnly, strictBpm/strictYear, stopIfUnresolved), which the schema largely documents itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("Build a draft playlist from artists and/or seeds") and immediately scopes it against siblings: nothing is written until create_playlist, and long builds are polled via get_draft. An agent can distinguish this from create_playlist, edit_draft, and get_draft 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.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use branches: Spotify login vs provider "deezer" with no account, and a concrete procedure for free-text requests (propose 15-30 artists yourself and add a matching genre seed). It also names the follow-up tool and condition (poll get_draft waitSeconds: 25 when status is "building").

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