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

Annotations only cover the safety profile (readOnlyHint, openWorldHint), so the description carries the behavioral load and does it well: it discloses that two summary blocks are trimmed (80% of payload), that `include_trajectory` is a chart payload, and the critical gotcha that a wider `days` will not return older crossing events. It is slightly muddled about whether `events` is a parameter or a response block, which keeps it from a 5.

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 view definitions are front-loaded and information-dense with little waste. The trailing sentence about the 25-event cap is a valuable gotcha but phrased in a somewhat tangled way ('a wider days is not what returns them').

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?

An output schema exists, so return values need not be re-explained, and the description covers the windowing, payload-trimming, and event-cap behaviors an agent needs to call this correctly. Ambiguity around `events` as param vs response block and absent sibling differentiation are the only lacunae.

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 description coverage is 0%, so the description must compensate, and it does: `days` is defined as the window both blocks are computed over, `include_trajectory` adds the full rank series, and each `view` enum value is explained semantically. Every parameter gets meaning beyond the bare schema.

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 (cluster-rotation layer) and enumerates exactly what each `view` returns (summary, laggards, discovered, members), so an agent can tell the four modes apart. It stops short of distinguishing this tool from any of the many sibling analysis tools, which is the one clear gap.

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 per-view descriptions effectively act as selection guidance (which view answers which question) and it notes `include_trajectory` is off by default. However there is no explicit when-to-use vs when-not, and no routing to any sibling tool for overlapping questions.

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