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

Annotations already declare a safe idempotent read, so the description focuses elsewhere and adds genuine context: the change metric is computed against a previous period of equal length, response time is measured in hours from review to posted reply, and by_platform only lists stores the selected apps actually occupy. The setup_required/syncing guidance ('do not report zero reviews') is real behavioral disclosure that prevents a damaging misinterpretation.

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-loaded with the purpose and metric list, then scope, then usage cue, then error-state handling — a sensible ordering with no filler sentences. It is dense and near the upper end of comfortable length, and the dangling by_platform clause is wasted text.

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 needn't be explained, and the description still helpfully previews what is aggregated plus the defaults inherited from the schema. Error-state and empty-data handling are covered. The only material gap is the reference to by_platform, which is absent from the schema and could send an agent looking for a parameter that isn't there.

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%, with defaults for since, until and app_id already documented, so the baseline applies. The description contributes a concrete example value for the timestamp format, but it also references a 'by_platform' parameter that does not appear in the input schema, which muddies rather than clarifies parameter behavior.

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 opens with a specific verb and resource ('Aggregate numbers for a period') and then enumerates the exact metrics returned: totals, period-over-period change, average rating, star distribution, response rate and response time. The scope ('for one app or all apps') is stated, which cleanly separates it from the row-level siblings get_app_reviews and get_review.

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?

'Use it for summaries and reports' gives the agent a positive selection cue against the list-style sibling tools. It also handles the two branch conditions an agent will actually hit (setup_required, syncing) with explicit instructions. It stops short of naming an alternative tool or stating when-not to use it.

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