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

Goes well beyond the readOnly/idempotent/openWorld annotations: it warns that `resolved_via: cluster` means observed rather than verified, mandates asking the user first when ambiguity.state is not none, flags untrusted_text as display-only (prompt-injection defense), states the credit-attribution requirement, and declares anonymous-or-linked auth.

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?

Tight, front-loaded labeled lines (Use / Inputs / Returns / Auth) with no filler. Some phrasing is telegraphic to the point of opacity ('Credit attribution.line'), which costs a little readability but nothing is wasted.

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 does the necessary work by naming returned fields (`cluster_id`, `display`, `slug`, `resolved_via`, `ambiguity.candidates`) and the escalation policy. The main gap is behavior when nothing resolves, and the unmentioned track/artist/isrc combination path for an 8-parameter tool.

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 a constraint the schema does not encode: 'one of `q`, `url`, `cluster_id`, `discogs_id`, `mbid`', which tells the agent these are mutually exclusive selectors even though required is empty. However, three of the eight parameters (isrc, track, artist) are never mentioned, and with 63% schema coverage those remain only partly explained.

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 and resource ('Map a name, URL or id to hosaka's verified artist identity (`cluster_id`)') plus the distinguishing output trait, an ambiguity verdict. It implies the split from siblings like get_artist (fetch by known id) and browse_artists, but never names an alternative explicitly, so sibling differentiation is left to inference.

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?

The 'Use:' line gives concrete triggering conditions ('the user names an artist; you hold a Discogs / MusicBrainz / Bandcamp URL or id'), which is clear context for selection. It stops short of explicit when-not-to-use or naming which sibling to call instead when the artist is already resolved.

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