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

Annotations already provide readOnlyHint=true, so safety is covered. The description adds meaningful behavioral context: 'Read-only', the cap on results and the 'capped=true' flag, and the caveat that 'an unscanned container is not a clean one'. It does not describe pagination behavior beyond page/page_size in schema, but covers the key non-obvious traits.

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?

Front-loaded with what is listed, then scope, then a warning about unscanned containers, then narrowing instructions, then cap behavior. Dense but every sentence carries information; slightly telegraphic in places but no wasted words.

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?

A read-only listing tool with annotations covering safety and schema covering all 7 parameters. The description covers scope, finding semantics, narrowing, and result cap. It does not explain container-level vs pod-level output structure in detail, but without an output schema this is a reasonable gap given the described fields.

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 100%, so baseline is 3. The description adds value by explaining the workload_kind + workload_name pairing and the workload_uid alternative, and by noting namespace omission behavior, but does not add syntax or format details beyond the 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?

States a specific verb (list) and resource (running pods with container scan findings), including the exact data fields returned (image, scanned status, severity counts, known-exploited, fixable-severe). Distinguishes from plain get_pods/list_security_workloads by emphasizing per-container scanner findings.

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?

Gives explicit narrowing instructions: 'Narrow to one workload with workload_kind + workload_name or workload_uid.' Also implies cluster/namespace scoping. Does not explicitly name alternative tools (e.g., get_pods for raw listing), but context for when to narrow is clear.

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