Mark tracks as recommended

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

Annotations already cover the safety profile (write, idempotent, open-world, non-destructive), so the description's job is to add semantics — and it does, disclosing that the write persists as history and permanently suppresses future suggestions, plus that this is an out-of-band repair operation. It does not state whether the effect can be undone or what a partial/invalid input does, and 'never suggested' sits in slight tension with destructiveHint=false.

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 short sentences, with the effect front-loaded before the usage constraint, and no wasted wording. The 'Repair tool:' prefix usefully frames the mode of operation in two words.

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 simple 2-parameter, non-destructive write with no output schema, the description covers the essential effect and the repair framing. It is still incomplete on two points an agent needs: how it relates to the `forget` sibling, and whether/how the permanent suppression can be reversed.

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%: `lane` documents the lanes.json id with an example, and `tracks` documents the 'Artist — Title' or Spotify-link format with 1–100 item bounds. The description adds no format, validation, or matching semantics beyond that, so the baseline 3 applies.

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 concrete effect on a concrete resource: adding tracks to the history so they are never suggested again, and it labels the tool as a repair path rather than a normal suggestion flow. That is clear enough to act on, but it never distinguishes this from the `forget` sibling, and the effect described (suppression) reads oddly against the name/title 'mark_recommended', which could mislead selection.

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?

'Repair tool' and 'Only use when asked' imply a narrow, exception-only usage context, which is genuinely useful guidance. However, 'when asked' is undefined, and no alternative is named — an agent cannot tell from this whether `forget` or another sibling is the correct route for removing a track from consideration.

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