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

The description adds real behavioral context beyond the annotations: it discloses that calls consume SEO add-on credits and explains how `language`/`location` values are normalized instead of being forwarded raw. But the annotations declare destructiveHint=true and idempotentHint=false, and the description – which frames the tool as simply 'Returns the text' – never explains what is destructive, whether refresh invalidates cached data, or what non-idempotency means here.

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?

The purpose is front-loaded and the core sentences earn their place, but the recounting of the past language-handling bug ('used to be passed straight to the data provider, which rejected it...') is background history that does not help an agent invoke the tool, since the accepted formats were already stated one clause earlier.

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?

An output schema exists, so return values need no explanation, and the description covers the key inputs for a five-parameter, one-required tool. The remaining gaps are `refresh` semantics and any reconciliation with the destructive/non-idempotent annotations, which leaves it one step short of complete.

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 0%, so the description carries the burden, and it mostly succeeds: `target` is defined semantically (your domain, cited-check), `language` gets accepted formats with concrete examples ('en', 'tr', 'English', 'Türkçe'), and `location` is shown as a country name. Only `refresh` is left unexplained, preventing a 5.

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 names a specific verb and resource – it returns Google's AI Overview answer text plus the sources it cites for a query – and explains that `target` reveals whether your domain is cited. It also differentiates itself conceptually from mention-count tools ('Goes beyond mention counts'), so an agent can distinguish it from the nearby GEO siblings without opening a schema.

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?

Usage is implied rather than stated: 'pass your domain as target to learn whether your site is cited' tells the agent the scenario, and 'Goes beyond mention counts' hints at an alternative class of tool. However, no sibling is named explicitly (e.g., seo_geo_citations, seo_geo_tracker) and there is no when-not guidance, leaving the agent to infer which GEO tool to pick.

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