Expand a playlist

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower. The description still adds real behavior: the default artist/track counts, the automatic exclusion of tracks already in the playlist, and the fact that the result is a draft rather than a published playlist. It doesn't mention that each call produces a new draft or any provider/auth requirement (left to the schema).

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?

Two sentences, no filler, with the core behavior and defaults front-loaded before the relationship to create_draft. Every clause carries information an agent needs.

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 20-parameter, non-idempotent mutation tool with no output schema, the description covers the essential behavior and the two defaults an agent must know, and the many filter options are self-documented in the schema. The main gap is that it doesn't signal that repeated calls yield distinct drafts, which matters given idempotentHint=false.

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?

Schema coverage is 70%, in the middle band, and the description adds genuine meaning for a few key knobs: tracksPerArtist default of 2 (not stated in the schema), the 30-artist cap, and the exclude-existing behavior. It says nothing about the remaining undocumented params (name, public, maxTracks, excludeArtists, tracksPerTier), so it only partially compensates.

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?

States a specific verb and resource ('Build a draft of more songs by the artists of an existing playlist') and immediately pins down scope with the defaults (2 per artist, 30 most frequent artists) and the exclusion rule. It also names the sibling it relates to ('shortcut for create_draft'), so an agent can distinguish it from create_draft and merge_playlists without opening either 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?

The description frames the tool as a shortcut for create_draft with a playlist seed plus excludeTracksFrom, which implicitly tells the agent when to reach for this rather than the general draft builder. It stops short of an explicit when-not (e.g. 'use create_draft instead if you are seeding from tracks rather than a playlist'), so a small inference remains.

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