list_anomalies

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

While annotations already indicate read-only, idempotent, and non-destructive, the description adds substantial behavioral detail: the two execution modes, performance characteristics ('One stats call per VM'), pagination envelope fields (items, returned, limit, total, truncated, hint, scanned), and the critical caveat that truncated=true means VMs went unscanned. This goes far beyond the annotations.

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 well-structured, starting with a concise summary, followed by context, behavioral details, return envelope explanation, and an Arg list. Every sentence adds value — the length is justified by the tool's complexity, and the formatting makes it easy to parse.

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?

There is no output schema, but the description fully explains the return envelope and its fields. It also covers the two call modes, edge cases (truncated flag), and performance implications. Given the complexity and the absence of an output schema, the description is complete enough for an agent to use effectively.

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 0% and the schema only provides types/defaults. The description compensates fully by explaining each parameter: resource_id (scope to a single resource), limit (max VMs to scan, 1–100, default 50), and target (Aria target name from config). This gives the agent complete context for invoking the tool.

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 "[READ] Report per-resource anomaly counts (System Attributes|total_alarms metric)", which is a specific verb and resource, and distinguishes from siblings by explaining this is the Total Anomalies metric not exposed in the UI. It clearly defines both usage modes (scoped by resource_id or scanning VMs).

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 context on when this tool is appropriate ('The suite-api does not expose the UI's anomalous-metrics list'), and explicitly directs to an alternative for deeper investigation ('For root cause, follow up with list_alerts(resource_id=...)'). It also gives operational advice ('keep limit modest'), but does not explicitly state when not to use it.

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