list_anomalies

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

With no annotations, the description fully carries transparency. It clearly discloses deduplication behavior (only one open event per anomaly type per cluster) and lists the four anomaly types. It does not mention rate limits or authentication, but the non-destructive nature of listing is implied.

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 concise: two initial sentences plus an Args section. No unnecessary words. Structure is front-loaded with main action, then details, then parameter specs. Every sentence adds value.

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 low schema coverage, the description adequately covers purpose, behavior, and parameters. It does not describe return format or pagination, which could be inferred. Still, for a listing tool, it is reasonably 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?

Despite 0% schema coverage, the description's Args section adds meaning beyond the schema: clarifying that cluster_name and status are filters, that status accepts 'open' or 'resolved', and that omitting status returns all. This compensates for the sparse schema.

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 lists GPU anomalies detected by VibOps across all clusters. It specifies the verb 'list' and the resource 'GPU anomalies', distinguishing it from siblings like get_open_anomalies which likely returns only open anomalies. The presence of optional filters further refines purpose.

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 anomalies are detected and their types, but does not explicitly guide when to use this tool versus alternatives like get_open_anomalies or list_alerts. The filtering info is helpful but lacks exclusionary criteria or alternative tool references.

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