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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds meaningful behavioral context beyond those hints: the 90-day per-day/per-country history, the up-to-20 sibling keyword limit, the inclusion of scheduled and generated articles, and the empty-history edge case when GSC is disconnected.

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?

Three sentences, each earning its place: the return payload, the important edge case, and the conditional parameter guidance. The most decision-relevant information is front-loaded.

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 single-keyword retrieval tool with a read-only annotation and an output schema, the description is complete. It covers what is returned, the limit on sibling keywords, the GSC dependency, and the parameter condition the agent needs to make a correct call.

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% and the schema already describes both parameters. The description adds a practical condition for website_id ('Pass website_id when the account has several websites') and references get_account, giving the agent actionable selection logic beyond the schema's static descriptions.

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: 'Returns one keyword with its metrics...' It clearly enumerates the exact payload components (metrics, 90-day position history, articles, sibling keywords), which differentiates it from siblings like list_keywords, get_keyword_rankings, and get_keyword_trends.

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 gives clear contextual usage guidance: it tells the agent when to pass website_id ('when the account has several websites') and warns when position history will be empty ('when Google Search Console is not connected'). It does not explicitly name alternatives or state when not to use this tool, so it stops short of a 5.

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