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

Annotations cover the safety profile, and the description adds genuinely valuable context beyond them: cost behaviour (no credits but TWO Search Console requests of the per-property quota per call), the external-source caveat that Google itself omits rare queries, and the row-cap caveat that can inflate the estimate. This is exactly the kind of undisclosed behavior an agent needs before calling.

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?

Front-loaded with the core mechanism before cost and usage detail; every sentence carries information. The state enumeration is dense but each entry is distinct and necessary, so length is justified rather than padded.

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?

There is no output schema, so the description carries the full burden of describing return semantics — and it does, explaining the `state` values and the `possiblyRowCapped` flag, including the critical distinction that `no_search_data` is an absence of data rather than zero anonymization. Nothing essential is missing for correct interpretation.

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%, so the schema already documents all four parameters, including enums, date patterns, and the ~16-month clamp / ~3-day lag. The description adds no parameter syntax beyond what the schema provides, so baseline 3 applies.

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+resource and an unusual, precisely defined one: it compares the sum of named per-query clicks/impressions against the property's true undimensioned total, with the gap being the anonymized volume. This is clearly distinguishable from siblings like get_search_console_performance and get_search_console_coverage.

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 explicit operational guidance ('ALWAYS narrow on `state` first') and enumerates the state values with their meanings, plus a conditional follow-up ('On `analysed`, ALWAYS check `possiblyRowCapped`'). It stops short of naming a sibling alternative for when this estimate is not wanted, but the when/how guidance is strong.

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