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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description still adds genuine context beyond them: that nothing changes until the person approves, that this is a proposal staged in the editor, and that repeated calls are the intended pattern for offering options rather than a mistake. It stops short of describing the returned payload, but an output schema exists so that burden is lifted.

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?

Five short clauses, front-loaded with the core action and the approval semantics before the parenthetical alternative and the exclusion. Every sentence carries a distinct constraint: source of ids, staging behavior, multi-call pattern, and the negative case. Nothing is repeated from the title or schema.

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 three-parameter, non-destructive proposal tool with full schema coverage and an output schema, the description supplies everything an agent needs to decide between it, list_music, set_music, and request_music_generation, plus how to batch calls. No behavioral dimension relevant to correct invocation is left unaddressed.

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 100%, so the baseline is 3; the description exceeds it by clarifying that musicId must originate from list_music and that each option's reason must be tied to this specific listing, which constrains the reason field's intent beyond its schema text ("One short sentence on why it fits"). What it does not cover is whether listingId has any interplay with the track choice beyond selection context.

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 names a specific verb and resource ("Shows one existing track ... for the person to play and approve") and immediately scopes the source of the input ("an id from list_music"). It explicitly distinguishes itself from three siblings: list_music (source of ids), set_music (applies directly), and request_music_generation ("Not for generating a new track").

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?

It states when to use it (proposing a track for approval in the editor), how to use it for multiple options ("Several calls in one step offer several options"), and when not to use it ("set_music applies a track directly", "Not for generating a new track"). Both the alternative tools and the conditions selecting them are named explicitly.

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