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

With annotations only covering the generic safety profile (not readOnly, not destructive, not idempotent), the description carries real behavioral weight: it discloses that the call consumes a metered run from the monthly allowance, that repeated calls are therefore expensive (consistent with idempotentHint=false), that AI variants hit a separate AI allowance, that the result is a run id rather than data, and that execution happens server-side with no local AI or store access. That is exactly the kind of consequence-level detail annotations cannot express.

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?

Everything is front-loaded: what it does, what it costs, what it returns, and how to continue. The long first sentence is dense with distinct facts rather than padding, and each following sentence adds a separate operational fact (cost, return value, execution model) with no repetition.

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 mutating, metered, asynchronous job with no output schema, the description supplies everything needed to call and continue correctly: the run id return value, the polling target, the allowance cost, and the fact that no local AI or store credentials are required. Nothing material is left for the agent to infer.

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 100%, so storefronts, use_ai, store, bundle_id and application_id are all already documented, and the description largely restates them (per-country candidates, AI variants when use_ai is true). It does add one clarifying point — that rule-based variants are written regardless of use_ai — but offers no syntax, defaults or format guidance beyond the schema, so the baseline of 3 fits.

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 ('Start an ASOClimb Wow Keywords run for an app') and then spells out the actual work: candidate keyword discovery per country, scoring, and rule-based plus optional AI listing variants. This clearly separates it from the sibling readers (wow_keywords_get, wow_keywords_status, wow_keywords_report) and the applier (wow_keywords_apply_draft).

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?

It gives clear operating context — this is the kickoff of an asynchronous job, and the agent should 'poll wow_keywords_status' afterward — plus the cost condition (one run from the monthly allowance) that governs when it's worth calling. It does not, however, say when to prefer it over the other keyword-discovery siblings such as discover_keywords or expand_keyword_gap, so there's no explicit exclusion.

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