get_keywords

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, closed-world), so the description correctly spends its budget elsewhere: it discloses the three-state result semantics (measured=false vs rank=null vs rank=<number>), which is real behavioral context an agent cannot get from annotations. It omits error/pagination behavior, but the state-semantics warning is genuinely valuable.

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, then the three states and the failure mode of collapsing them. 'Never collapse them into one' mildly restates the preceding 'THREE STATES ARE DISTINCT', but the closing clause adds the rationale (false zeros) and earns its place.

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 bears the burden of explaining return semantics and does so well for the critical rank/measured distinction. It does not say what keyword set or time range is returned (there is no date or keyword parameter), leaving some ambiguity about result breadth, but the highest-risk interpretation trap is covered.

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 appId, country, and platform are already documented in the schema; the description only echoes the one-app/one-country scope. Baseline 3 is appropriate — it adds no format or syntax detail beyond the schema (e.g., how country defaults interact with platform).

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: keyword ranks for one app in one App Store / Google Play country, with explicit scoping that excludes multi-app or multi-country use. It never names the near-siblings it could be confused with (check_rank, get_keyword_metrics, hive_keyword_ranks), so differentiation is left implicit.

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 scoping ('one app in one country') implies when the tool applies, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many keyword-related siblings. Usage must be inferred from scope alone.

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