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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior. The description adds meaningful context beyond that: collection ordering, cursor consistency requirements, sample-based results, and untrusted review content.

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?

Four concise, front-loaded sentences each carry operational guidance without wasted wording. The minor defect is the 'nextCursor' reference, which does not match the schema's 'cursor' parameter name and could confuse invocation.

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?

For a nine-parameter search tool with partial schema documentation and no output schema, the description covers result trust, sampling, and ordering well. It remains incomplete on filter parameter usage and return-value expectations, leaving meaningful gaps.

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?

There are 9 parameters and only 44% schema description coverage, so the description needs to compensate. It mentions only cursor-based pagination, and does so as 'nextCursor' rather than the schema's 'cursor'; it does not explain appId, query, since/until, ratings, locale, version, or limit semantics.

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 verb and resource: 'Search collected reviews,' and adds ordering with 'newest collection first.' It does not explicitly distinguish this from siblings such as get_review or get_review_stats, so it stops short of 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?

Provides useful pagination guidance ('Follow nextCursor with identical filters') and an interpretation caveat ('evidence samples, not whole-store totals'). However, it never states when to choose this tool over get_review, get_review_stats, or list_apps, so usage is only implied.

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