Apple Music

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses the per-call credit pricing, that failures are free, that responses report charged and remaining credits, that pagination uses an opaque cursor, and that caching yields zero-cost calls. This is exactly the behavioral context an agent needs before spending credits.

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 mechanics followed by a compact per-resource bullet list, with no wasted prose. Minor duplication with the schema: the cursor pass-back rule and the free-cache rule for `max_age_days` restate what the parameter descriptions already say.

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 an 8-parameter, nested-`params`, resource-dispatching tool it covers selection, argument placement, pricing, pagination, and caching, and it notes the response reports credit charge and balance. With no output schema, the description could say more about the shape of returned album/artist/track objects, and it never mentions `region`.

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 baseline is 3; the description adds real meaning by mapping parameters to resources (url|id for album/artist/track, query for search) and by introducing an optional `type` for search that is not a top-level schema property. It doesn't clarify `region` or the shape of `params` beyond pointing at `describe`.

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 the domain (Apple Music) and enumerates the four selectable resources with what each returns, so an agent can distinguish it from siblings like spotify or soundcloud. It loses a point for the verbless opening ("Data from Apple Music") and for listing "profiles" as a data type when no profile resource exists in the enum.

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 gives concrete calling mechanics: pick a resource, pass its params top-level, extras in `params`, pass `cursor` back for paging, use `max_age_days` for a free cached copy. It does not explicitly compare against sibling platform tools or say when Apple Music is preferable, which keeps it short of a 5.

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