keyword_report

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered elsewhere. The description adds 'bounded', implying a capped result window that matters for planning pagination, and flags that empty-metric rows are optional rather than default. It says nothing about rate limits, row caps, or async behavior expected of a reporting endpoint over an open-world API.

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?

A single front-loaded sentence with no filler; the scope ('bounded') and the notable option ('EMPTY_METRICS') come first. It is efficient but so short that the terseness shades into under-specification rather than economy.

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 an output schema, annotations, and full parameter coverage, much of the burden is offloaded, so the description need not explain return values or safety. However, for a 10-parameter reporting tool, it leaves the relationship between filters/groupBy/sorting and the result rows entirely to the schema, and gives no guidance on how to position this tool among the many sibling report tools.

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 100%, so every parameter including includeZeroMetrics ('include keywords with no metric rows by requesting EMPTY_METRICS') is already documented. The description's EMPTY_METRICS reference merely restates that schema text and adds no new semantics for filters, groupBy, sorting or timeRange.

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?

Clear verb+resource+scope: 'Read bounded keyword performance rows' tells an agent this is a read-only reporting tool scoped to keyword-level metrics, distinct from keyword_get or keywords_query. It never names a sibling report tool (ad_group_report, search_term_report, ad_report) to sharpen the boundary, so differentiation is inferred rather than stated.

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?

No when-to-use or when-not guidance beyond 'bounded' hinting at pagination. It does not say to prefer this over keyword_get when the agent needs metrics, nor over search_term_report when the agent wants query-level data. The only semi-useful hint is the EMPTY_METRICS mention, which still requires the agent to know which parameter enables it.

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