set_target

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

With no annotations, the description carries the disclosure burden. It does disclose meaningful behavior: value semantics per kind, median aggregation for artist/favorites, and returned acceptance ranges plus outlier warnings. It does not state whether the target is persisted or applied to the current session or how it interacts with session/undo, leaving some behavioral ambiguity.

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?

The definition is compact, front-loads the core purpose, and uses a scannable bullet list. The only minor issue is that the schema parameter names could have been aligned more explicitly with the bullet items.

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?

It covers target kinds, value semantics, and the return payload shape despite the output schema being present. It is incomplete regarding the `genre` parameter, side effects on the current mix/session, and how 'blank' is represented, which matters for an agent with no annotations and 3 free-form parameters.

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?

The description adds substantial meaning for `kind` and `value`, explaining valid values and per-kind behavior; schema coverage is 0%, so this compensation is necessary. However, the `genre` parameter is never explained, and its relationship to `value` for genre targets is ambiguous, leaving an agent unsure which field to populate.

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 opening sentence uses a specific verb ('Choose') and a clear resource ('what the mix is steered toward'), and the bullet list concretely defines the kinds of targets. It does not explicitly differentiate itself from sibling tools like project_reference or find_references, so it falls just short of a 5.

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?

Usage is implied: an agent should call this when it wants to set the mix target, and the kind list indicates when each target form applies. However, there are no explicit conditions for when to use this versus alternative tools, no prerequisites, and no mention of when not to use it.

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