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

With readOnlyHint, idempotentHint, and destructiveHint already declaring safety, the description goes further by disclosing the data source ('pooled record of every search'), the non-existence of an Apple endpoint, and the implication that results are limited to what has been observed. This is meaningul behavioral context that helps the agent set expectations about sparse results, and it contradicts nothing in the annotations.

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?

Two sentences with no waste. The core meaning is front-loaded, and each additional clause earns its place by explaining the data pool and the practical limitation. The structure makes it easy for an agent to quickly grasp both the action and the caveat.

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?

The tool is well covered by annotations (read-only, idempotent, non-destructive) and a complete input schema. The description supplies the remaining crucial context: it is cross-account, relies on observed data, and may return little for unswept apps. For a read-only query tool with no output schema, this is sufficient for an agent to select and invoke it correctly.

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 the baseline is 3. The description adds signifcant value beyond the schema for the appId parameter by specifying it can be any App Store id, not only account-owned, and by explaining that results for an app depend on prior sweep coverage. This nuances 'App Store app id' in a way that directly affects invocation and interpretation. Other parameters (limit, country, maxRank) gain nothing beyond the schema, but the added appId context justifies a 4.

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 precise statement of what the tool does: 'Which keywords an app is already ranking for.' It names the resource (ranking keywords), the scope (per app), and adds a distinguishing capability: it works on any App Store id, including rival apps. This clearly separates it from siblings like list_keywords or get_keyword without needing to reference them explicitly.

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?

The description provides clear usage context: it can be pointed at any app, including a rival, and it relies on observational data from prior searches. However, it does not explicitly state when to use this tool versus alternatives like keyword_competitors or get_keyword, nor does it give when-not-to-use conditions. Context is clear, but exclusions and explicit alternatives are absent.

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