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

Goes beyond the annotations by disclosing that earlier picks are replaced (the destructive-ish consequence the hints don't spell out), that the call is free and does not consume a lookup, and that the user should be told the items landed in the Action Center. Replacement of earlier picks is consistent with idempotentHint=true. It omits failure behavior, such as what happens if keywords aren't from the latest results.

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 tight sentences, front-loaded with the action and limit, followed by selection criteria and then the user-facing message. Minor repetition of 'Action Center' and a slightly scattered mix of rules, but no wasted sentences.

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-parameter tool with no output schema and annotations already covering the safety profile, the description supplies effect (items created, earlier picks replaced), cost, selection guidance, and the follow-up to tell the user. Nothing an agent needs to call it correctly is missing.

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 already documents the keywords array, so the baseline is 3; the description adds real meaning by stating the cap of 4 and the exclusion rules for what counts as a good keyword. It does not restate the 'exactly as the latest results listed them' formatting requirement, but the schema covers that.

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 and resource ('Puts up to 4 keywords ... in the Action Center as "Win the Google search …" items') and ties the input to a named sibling, find_keyword_opportunities. An agent can distinguish this from find_keyword_opportunities (discovery) without opening either 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?

Gives clear selection criteria (pick ones worth going after, skip other companies' products and brand names, skip near-duplicates) and implies use only after a find_keyword_opportunities run. It does not state explicit when-not conditions, e.g. what to do if nothing qualifies or how to handle an empty result.

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