list_anomalies

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully reveals the anomaly contents (name, metricSet, dimensions, metric, timelineSpec), the condition for inclusion (flagged only when the metric got worse), and pagination details (default 10, max 100, nextPageToken). This goes well beyond what the schema alone communicates, making the tool's behavior predictable.

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?

The description is a well-structured paragraph of five sentences, each earning its place: definition, data structure, workflow guidance, pagination, and entry-point advice. It is front-loaded with the core purpose, and there is zero redundancy or fluff.

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?

Despite lacking an output schema and annotations, the description is complete enough for an agent to invoke the tool correctly and process results. It covers the return fields, pagination behavior, and next steps (feeding into query_* tools). Given the moderate complexity (pagination, filter), the description fully compensates for missing structured output schema.

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?

The schema already covers all 4 parameters with descriptions, so the baseline is 3. The description adds meaningful context beyond the schema: it explains what 'dimensions' represent (e.g., versionCode or deviceModel), clarifies the anomaly metric and timelineSpec, and reinforces how page_token works with nextPageToken. This enriches the schema rather than merely repeating it.

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?

The description clearly states the tool's function: 'List anomalies Google detected in this app's vitals metrics' – a specific verb and resource. It also distinguishes this from sibling query_* tools by framing it as the entry point for checking current problems, and explains the anomaly data structure, making its exact purpose unambiguous.

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 explicitly advises using this tool first ('Start here to check whether anything is currently wrong instead of guessing date ranges') and directs feeding results into the matching query_* tool for timelines. It gives clear contextual guidance on workflow placement, though it doesn't explicitly state when not to use it (e.g., if the exact metric is already known, one could go directly to query_*).

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