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

Annotations (readOnlyHint, openWorldHint) provide a baseline, but the description adds rich behavioral detail: trimming two blocks because they are 80% of the response, include_trajectory being off by default and adding a chart payload, and events returning the newest 25 crossings with a caveat about exactly 25 indicating older ones. This goes well beyond annotations and paints a clear picture of what the tool does internally.

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 description is a single dense paragraph without clear sectioning. It front-loads the purpose but quickly dives into details about trimming, events, and trajectory without a logical order. Multiple ideas (views, trimming, events limit) are packed in, making it longer than necessary and harder to scan. It's not elegantly structured, though it conveys needed info.

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 an output schema present, return values are covered, but the description still has gaps. It explains summary and include_trajectory well, but laggards/discovered are only one-liners. The 'events' mention is ambiguous (not in the view enum), and it doesn't clarify whether days applies to all views. For a tool with 3 parameters and 4 distinguished views, the description is not fully complete.

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 0%, so the description must explain parameters. It does: view is explained with one-liners for each enum value, include_trajectory is described, and days is tied to the summary window. However, it introduces an 'events' concept that isn't a parameter and explains only summary's window control, leaving laggards/discovered/members' dependence on days ambiguous. This adds value but is incomplete and slightly confusing.

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 purpose: 'Cluster-rotation layer' and enumerates distinct views (summary, laggards, discovered, members) with brief roles. Clearly describes what it does, but does not explicitly differentiate from sibling tools such as rayana_ai_rankings or rayana_ai_trends, which might overlap. The name and domain strongly imply the purpose but without naming alternatives, it stops short of a 5.

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?

No explicit guidance on when to choose this tool over alternatives. It describes internal behavior and options but never states a typical use case, prerequisite, or exclusion. For instance, it doesn't say 'use this when you need cluster rotation data' or contrast with siblings. The usage context is only implied by the tool's name and domain vocabulary.

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