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

Beyond the annotations (readOnly, idempotent, non-destructive, open-world), the description discloses real operational context: the tool is disabled while the protection ladder is raised (`tool_disabled`, `ladder_L1`), output carries a credit attribution line, ambiguity must be resolved before proceeding, `untrusted_text` is display-only, and auth is required. This is exactly the context structured fields cannot carry.

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 line-per-facet layout (Use / Inputs / Returns / constraints / Auth) is front-loaded and scannable with no filler. It is dense but every line carries operative information; minor cost is jargon ('hosaka', 'ladder_L1') assumed known.

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 correctly supplies the return shape (`data.items[]` with field names), plus the disabled condition and auth requirement, so an agent can invoke it and interpret the response. The remaining gap is routing versus near-identical siblings like `list_ones_to_watch`.

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 only 33%, so the description must compensate. It restates `limit` 1–50 default 8 and lists the enum values for `tier` and `corroboration`, but never explains what a `booking_ahead` corroboration or a `rising` tier actually mean — the agent gets the vocabulary without semantic grounding.

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 names the resource (artists) and the precise qualifier (breaking out or rising, with observed corroboration), so an agent knows this is a curated discovery list, not a general artist search. It does not, however, distinguish itself from the close sibling `list_ones_to_watch` or explain what 'hosaka' scoring means.

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: who is breaking through now.' gives a clear situational trigger, which is more than most tools offer. But no alternative is named and no exclusion is stated, even though `list_ones_to_watch` and `browse_artists` plausibly overlap — the agent must infer which to pick.

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