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

Beyond the readOnly/idempotent annotations, it discloses the 7-day cache, the 30-120s cold-run cost, and — critically — that results can come back with mode:"agent" requiring the caller to do the clustering itself. That conditional-response contract is exactly the kind of trait annotations cannot express.

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?

Front-loads the core purpose, then layers output shape, latency/caching, and the agent-mode caveat in a tight sequence. Every sentence carries distinct information with no repetition of schema content.

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?

There is no output schema, but the description fully covers the return shape (title, sharePercent, severity, verbatim quotes) and the alternate agent-mode payload with instructions. An agent knows both what it gets and what it may need to do next.

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 100%, so all seven parameters (appId, store inference, analyze modes, review tiers, maxRating) are already documented in full. The description adds no further parameter guidance, so the baseline 3 applies.

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 precise verb chain (fetch reviews → filter negatives → cluster into ranked pain points) and enumerates the output fields. It is clearly distinguishable from the sibling get_app_reviews, which only fetches raw reviews.

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?

"Ideal for competitive research and product discovery" gives clear context, and the cold-vs-cached latency note plus the mode:"agent" fallback tells the agent what to expect and what extra work it may have to do. It stops short of explicitly naming when to prefer get_app_reviews or get_pain_trend instead.

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