gsc_anomalies

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

With no annotations provided, the description carries the full burden, and it delivers extensive behavioral guidance: it instructs the agent to base analysis only on returned data, report exact numbers, avoid speculating on causes without data support, and admit when data lacks information. It also mandates a specific dashboard-like presentation style. This goes well beyond a typical tool description.

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 structured with clear sections (core, IMPORTANT, PRESENTATION) and leads with the core purpose, but it is quite verbose, especially the presentation instructions which consume a large portion. Every sentence adds value, but the length may tax the agent's context; still, it's efficiently organized with key behavioral rules.

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?

Given no output schema and no annotations, the description provides a remarkably complete picture: purpose, usage context, data prerequisites, analysis rules, and presentation requirements. The only omitted detail is the exact data return structure, but the presentation instructions imply a structured dashboard, making this sufficient for a 2-param tool.

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?

Input schema already describes both dataset and anomaly_threshold with 100% coverage, so the baseline is 3. The tool description adds no extra parameter-level detail beyond the schema, though it does mention the data history requirement, which is indirectly related to the dataset parameter. No further compensation needed.

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 opens with a specific verb+resource ('Detect traffic anomalies using BigQuery ML') and immediately distinguishes itself from traditional threshold-based alerts by explaining it accounts for seasonality and weekly patterns, setting it apart from sibling tools like gsc_alerts. This makes the tool's purpose unambiguous and clearly differentiated.

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 provides clear context for when to use it: it's for detecting genuinely unexpected traffic changes rather than simple threshold alerts, and it explicitly notes the need for at least 6 months of historical data. It lacks explicit named alternatives or a direct 'use this when...' formula, but the prerequisite and comparison give sufficient guidance.

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