get_metric_anomalies

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

Annotations already cover the read-only, non-destructive, idempotent nature of the call, so the description's burden is lower. It adds the z-score/mean-deviation interpretation but does not disclose behavior such as how multiple methods are selected or what shape the anomaly results take.

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?

Two short sentences with no filler; the primary action is the first phrase and the explanation is immediately valuable. The only minor flaw is that the z-score mention is not fully accurate for all schema methods, but the structure itself is excellent.

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 7-parameter analysis tool with no output schema, the description is too thin: it never states what the caller receives (anomaly scores, timestamps, datapoint names) or how required IDs scope the computation. A sentence covering the return shape would make it complete.

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?

All seven parameters are documented in the schema, so the description does not need to repeat them. It adds only a high-level connection between deviation-from-mean and threshold semantics, matching the baseline for full schema coverage.

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 the core operation ('detect metric anomalies') and a defining technique ('z-score analysis'), so an agent can tell it apart from data-retrieval tools like get_device_data. However, the z-score framing is narrower than the schema's full method enum (auto, iqr, mad), slightly under-specifying the tool's scope.

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 guidance on when to choose this tool over siblings such as detect_change_points, forecast_metric, or compare_to_baseline. The only implied trigger is generic 'detect anomalies,' with no exclusions or alternative routing.

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