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

Annotations already cover the read-only/idempotent safety profile, and the description adds substantive semantics beyond that: values are cached daily, installs are summed across versions, revenue is net and grouped by original currency, subscriptions are non-additive daily snapshots, and missing rows mean unknown rather than zero.

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?

Five short sentences, each carrying a distinct fact, with the scope and window stated first and the data caveats following. No filler or restatement of the title.

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 no output schema, the description does the necessary work of explaining return-value semantics (row cap, unknown-vs-zero, currency grouping, micros scaling). Only the platform parameter's role is left unexplained.

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 has to carry the load; it explains the date window (max 90 days, default 30) and the meaning of all three metric enum values, including the amountMicros integer-string convention. It says nothing about appId or the platform enum (APPLE/GOOGLE), leaving those to 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?

States a specific verb and resource ('Daily cached metrics for one app') plus the window constraint, which cleanly separates it from siblings like get_app and list_reviews. An agent can tell what this returns without opening the schema.

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?

Gives clear context for use — per-app daily metrics, defaults to 30 days, capped at 90, 1000-row ceiling — but never names an alternative tool or states when not to use it (e.g. multi-app comparison vs list_apps).

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