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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), the description discloses the empty-result behavior ('present:false without a signal'), the absence of ranking ('no composite score'), the display-only untrusted_text constraint, credit attribution.line, and 'Auth: linked'. That is meaningful behavior an agent cannot infer from structured fields.

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 and label-segmented (Use/Inputs/Returns/Credit/Auth), with no filler sentences. The telegraphic phrasing ('Credit attribution.line', 'hosaka observed') is dense enough that some terms require prior context, costing a little clarity.

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 specifies the return shape (data.similar[] {cluster_id, name, axes}), the no-signal case, and the auth requirement. Nothing an agent needs to invoke it correctly or interpret the response is missing.

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% — `key` is undocumented in the schema — and the description fills that gap by specifying it is a cluster_id from resolve_artist or a slug, which is the single most important calling detail. `limit` range and default are also restated with the failure mode (range_too_large above 25).

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 resource and scope: 'Artists adjacent to one artist', plus the exact axes observed and the explicit exclusion 'no composite score'. It also positions itself relative to resolve_artist ('cluster_id from resolve_artist'), which separates it from the lookup siblings like get_artist.

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?

'Use: artists like X; a listening path from a verified artist' gives concrete triggering scenarios, and the ambiguity/ask-first rule adds a decision gate. It stops short of naming an alternative tool or a when-not case, so it is clear context rather than full routing guidance.

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