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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=true, so the safety profile is covered. The description adds genuinely non-obvious workflow context beyond that: this call does not confirm labels and a human must confirm them in the studio before mixing, preventing an agent from assuming the labeling is final.

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, both earning their place, with the action stated first and the confirmation caveat second. Slightly awkward phrasing ('what is on each stem from what the person says') costs a little, but there is no 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?

For a two-parameter, no-output-schema tool the description covers the action, the input provenance, and the downstream human-confirmation gate. It omits what the call returns and whether existing labels are overwritten, which is a minor gap given the destructiveHint annotation.

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 50% at the top level, but the labels enum and its item description are unusually rich, and songId is documented. The description adds only the provenance detail that stemId/file names come from get_song_status; it does not explain batching, ordering, or what happens to previously set labels. Baseline 3 is appropriate.

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+resource ('Sets what is on each stem') and the source of truth for the input ('what the person says about their files'), plus names get_song_status as the origin of stem ids. It is clearly distinguishable from mixing/mastering siblings, though it doesn't explicitly contrast with them.

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?

Gives clear context for use: call it after get_song_status to obtain stem ids and file names, and note that human confirmation ('Labels are correct' in the studio) is a separate later step. No alternative tool is named because none competes, but no explicit when-not guidance is given either.

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