suggest_keywords

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

Annotations already flag non-read-only and non-idempotent behavior, and the description adds information annotations cannot carry: consumption of one AI writing credit from the monthly allowance (Pro and above) and the exclusion of already-known keywords. It stops short of describing latency, whether results are cached/reproducible, or what happens on credit exhaustion.

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 core purpose, then scope, then exclusions, then cost and next step. Information-dense with little waste, though the single long middle sentence covering output format, exclusions, and language could be split for easier scanning.

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?

There is no output schema, and the description compensates by specifying what comes back: 1–3 word search terms, each with a one-line justification naming the searcher and the need answered. Combined with the credit cost and exclusions, an agent has enough to call this 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 coverage is 100%, so the baseline is 3, but the description goes beyond the schema by tying lang to 'the language of the reasons' and cc to the storefront search language the terms are written in, which clarifies the per-storefront behavior that drives both parameters. It does not restate defaults (first country, en), which the schema already covers.

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 concrete verb+resource: generating new keyword ideas for one app in one storefront, with the output shape (1–3 word terms plus a one-line reason). This is clearly distinguishable from siblings like get_keyword_metrics (measurement) and add_keywords (tracking), which keeps it from being confused with the discovery/creation path.

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?

Explicitly routes the agent to get_keyword_metrics before tracking ('measure the ideas with get_keyword_metrics before you track them') and rules out material the tool will not return (tracked keywords, buried keywords, brand names). It does not, however, contrast itself with adjacent discovery tools like get_keyword_gap or hive_keyword_spy, so the alternative-selection guidance is partial.

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