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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses non-obvious operational behavior: the tool returns tool_disabled with reason ladder_L1 while the protection ladder is raised, present:false is the expected normal outcome for one-dimension artists, ambiguity.state requires asking first, and untrusted_text is display-only. Those are exactly the failure and safety modes an agent cannot get 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?

Labeled lines (Aura / Use / Inputs / Returns / Auth) front-load the core concept and keep the definition short with no filler. The telegraphic style is efficient but a few fragments ("Credit attribution.line", "untrusted_text is display-only") are compressed almost to keyword form and could cost a moment of parsing.

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 carries the return contract itself by naming data.items[] and data.aura fields (cluster_id, artist_name, convergence_dim_count, break_odds). Combined with the disabled-state, ambiguity, and auth notes, an agent has everything needed to call it and interpret the response correctly.

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%: limit is documented in the schema but cluster_id has no description. The description fills that gap by stating cluster_id comes from resolve_artist and may be omitted for an index listing, and it restates the 1–50 limit range with a default. It adds real semantic value on the undocumented parameter, though it does not say what the index ordering is.

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 concrete measurement: signal dimensions converging on an artist within 18 months plus a measured 12-month break probability, and the first line of Use pins the intent ("is an artist about to break"). It is specific enough to separate from generic lookups like get_artist, but it never names the closest siblings (list_breakouts, list_ones_to_watch), so the differentiation is implicit rather than stated.

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?

Gives an explicit use condition ("is an artist about to break") and a concrete routing rule for the optional parameter: take cluster_id from resolve_artist, omit it for the index view. It stops short of exclusions, i.e. it never says when to prefer list_breakouts or list_ones_to_watch instead, so an agent has context but no negative guidance.

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