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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; 'Changes nothing.' is a harmless restatement rather than new information. The description does add genuine behavioral detail beyond annotations, though: results are sorted biggest-first, entries the account already targets or blocks are flagged in_account, and bid ranges are rendered in the account's currency.

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?

One dense sentence with the resource and return fields front-loaded, no filler. It is slightly overloaded with listing output fields that the agent could infer, but every clause carries information.

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 usefully enumerates the return fields, sorting, in_account flagging, and currency, and annotations carry the safety profile. Minor gaps remain (empty-result behavior, whether ideas are capped by 'limit' default 50 vs max 200), but these are covered in the schema.

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% with rich per-parameter descriptions (language IDs, geo IDs, seeds limit of 20, min_searches), so baseline 3 applies. The description only adds that seeds and URL are combinable ('and/or') and that monetary values use account currency; it adds nothing about limit, min_searches, or location_ids beyond the schema.

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: 'Google Keyword Planner ideas from seed keywords and/or a landing-page URL', and enumerates the returned fields (average monthly searches, competition, top-of-page bid range). An agent can tell this generates keyword ideas rather than looking up metrics, though it never names the closest sibling (keyword_metrics) to draw the boundary explicitly.

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?

'From seed keywords and/or a landing-page URL' implies the two entry modes, which is useful usage context. However, there is no explicit when-to-use/when-not or a named alternative such as keyword_metrics for cases where the agent already has a keyword list and only wants metrics.

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