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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds genuine context beyond them: per-call credit costs, the cost difference between depths, and that failed answers are free. It stops short of describing the answer payload's shape or failure modes beyond billing.

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 purpose, then depth behavior and cost. Every clause carries information an agent needs (cost, defaults, failure billing); no filler.

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 an 8-parameter, no-output-schema tool, the description covers the core decision (depth) and cost model, which is what most agents need. Gaps remain around the output format of the cited answer and how time/country/language filters affect results.

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 50%, and the description usefully explains the two undocumented depth enum values and ties num_sources to depth=standard. However, time, country, language, exclude_domains, and the interaction between depth and num_sources limits remain unaddressed, so compensation is partial.

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 (answer a question) and resource (live Google results) plus the output form (numbered citations). This is clearly distinct from siblings like search, research, or extract, which return raw results rather than a synthesized cited answer.

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 frames the depth choice: fast answers from the result page for 3 credits, standard reads top pages for 8 credits at 3 sources. That is real selection guidance, but it doesn't say when to prefer this tool over search/research siblings or when to avoid it.

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