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

Annotations already declare readOnly/openWorld/idempotent, and the description adds real context on top: it performs a live fetch ('reads ... now') against the store, evaluates supplied extras, and persists nothing. It does not cover latency, rate limits, or failure modes for an external store fetch, which keeps it below 5.

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?

A single tightly-packed sentence front-loads the scope ('Check any App Store or Google Play listing, tracked or not') before the mechanics, and 'Stores nothing' lands as a useful closer. The colon clause is dense with three stacked ideas, but nothing is truly wasted.

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 10-parameter tool with no output schema, the description never says what the 'metadata checks' actually return (which checks, what findings or fields). The store/field mapping is covered well, but an agent cannot anticipate the result shape at all.

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 90%, so the baseline is 3, but the description adds genuine meaning: it explains *why* subtitle and keywords must be supplied (only the public title/description are read) and which values are yours to provide. It still doesn't clarify how `candidates` differ from `keywords` beyond the schema text.

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?

Specific verb+resource: 'Check any App Store or Google Play listing' plus what it acts on (public title/description and supplied subtitle, keywords, terms) and that it runs metadata checks. It implicitly separates itself from stored-metadata siblings via 'tracked or not' and 'Stores nothing', but never names get_metadata / simulate_metadata / compare_metadata_draft, so the differentiator is inferred rather than stated.

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?

'tracked or not' explicitly widens the use case beyond apps already in the account, and 'any subtitle, keyword field or terms you supply' tells the agent when to pass optional fields. It gives clear context but no exclusions or named alternatives, so an agent must still guess why it would pick this over simulate_metadata.

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