surprise_me

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

No annotations are provided, so the description carries the full burden — and it delivers. It explicitly discloses the mutation ('1 write (PUT /me/player/play)'), the quota cost ('1-3 reads'), and seedable reproducibility. This is strong transparency for a playback-affecting tool. It stops short of covering device-selection behavior or failure modes like an empty library or no active device.

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 tight sentences with zero waste. The core behavior is front-loaded first, followed by the seed capability and quota cost. Each sentence earns its place, and the quota note is compact operational context rather than filler.

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?

The core behavior, write operation, and quota are well covered, and the schema fully documents all 5 parameters. However, with no annotations and no output schema, the description omits practical context an agent needs: default device behavior, what happens with an empty library, and whether current playback is interrupted.

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 description coverage is 100%, so the baseline is 3. The description's seed mention ('Randomness seedable via seed for reproducible picks') largely duplicates the schema's own seed description. It adds no extra meaning for type, device_id, dry_run, or response_format beyond what the schema already provides.

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?

The description states a specific verb and resource: 'picks a random saved track, saved album, or owned playlist and plays it.' The scope is precise about which item types are eligible, and the play action makes the tool's function unmistakable even against a large sibling list containing similar random-pick tools.

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 behavior description implies when to use it (user wants a random surprise pick played from their library), but there is no explicit alternative routing or exclusion. With siblings like saved_tracks_roulette, daily_pick, and continue_last present, an agent receives no guidance on how to distinguish this tool from them.

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