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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds real value beyond that: it discloses the cascade (stems are deleted too), the external side effect (the share link stops working), and irreversibility, which the boolean hints cannot convey.

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?

Three short sentences, each earning its place: what is destroyed, the downstream consequence, and the required caution. The most important fact (permanent deletion) is front-loaded.

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?

With no output schema, the description still tells the agent the key outcome (link stops working) and the risk profile. It omits permission/auth requirements and any error behavior, but for a single-parameter destructive tool the coverage is nearly sufficient.

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?

Only one parameter (split_id), and the schema already documents it fully with a pattern and a pointer to split_songs/list_my_songs. The description adds nothing about the identifier format or source, so the schema does all the work — baseline 3.

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 (permanently delete), the exact resource (the connected account's song and its stems), and scope. It is clearly distinguishable from siblings like rename_song, split_songs, and list_my_songs without opening any 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?

"Confirm with the user first" gives a clear precondition for invoking it, and the irreversibility note implies when not to reach for it casually. However, it names no alternative (e.g., rename_song) for users who want to modify rather than remove a song, so routing guidance is only implied.

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