google_query_vitals

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

With no annotations present the description must carry the load, and it does disclose key behaviors: the default window is bounded by data Google actually has (a freshness lag the agent would otherwise miss), and rates are returned verbatim with no transformation. It still omits permission requirements, rate limits, and whether results are paginated or capped by maxRows, so it falls short of full disclosure.

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?

Four sentences, front-loaded with the metric scope before the optional dimension breakdown and defaults. Dense but essentially waste-free; the final threshold sentence is the least load-bearing and could be trimmed.

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 9-parameter tool with no annotations and no output schema, the description covers metric selection, dimensions, and the default window but says nothing about the shape of returned data (rows, rate fields, how metrics arrays override metricSet, how maxRows truncates). An agent can call it, but cannot predict the response structure.

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 78%, so the schema already documents most parameters including the date format, the AIP-160 filter syntax, and the dimension examples. The description largely restates what the schema says (dimension names, default window) rather than adding new parameter semantics; the one genuinely additive note is that crash and ANR defaults already include the user-perceived 28-day rates.

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 (Query) and resource (Android vitals) and enumerates the metric families covered (crash, ANR, slow start, slow rendering, wakeups, wakelocks, LMK, memory, error counts) plus the aggregation grain (by day). It does not explicitly name sibling tools such as google_search_vitals_error_issues or google_list_vitals_anomalies, so the agent must infer that this is the aggregate-metrics tool rather than the error-detail tool.

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?

The description explains the default time window ('last 28 days that Google has data for') and why crash/ANR defaults matter for threshold comparison, which implies when the tool is appropriate. However, it never states when to prefer it over the vitals siblings (error issues, error reports, anomalies) or any prerequisites such as needed permissions.

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