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

Annotations already declare readOnlyHint=true, so "Read-only" is largely redundant, but the description adds genuinely useful behavior: the one-row-per-image aggregation, the default sort column (risk_score), the sortable fields, and the fact that filters mirror list_security_findings. It does not describe pagination or result ordering beyond sort default, so it is short of the richest tier.

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-loads the core verb and scope in one dense sentence, then adds two short sentences for read-only status, sorting, and the primary use case. The enumeration of returned columns is long but earns its place given there is no output schema; nothing is clearly wasted.

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?

With no output schema, the description correctly compensates by listing the returned columns and granularity, plus default sort and shared filters. It omits pagination behavior and the default status/disposition behavior, though the latter is covered in the schema, so it is complete enough for correct invocation.

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 description coverage is 100%, so the schema already documents all 12 parameters in detail; the baseline is 3. The description reinforces sort semantics and the shared filter set with list_security_findings, but its sort list is actually narrower than the schema's (omits priority, image_ref, cluster_name, addon_attribution), so it adds emphasis rather than new meaning.

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 (security workloads carrying findings across the fleet) and pins the row granularity to one workload container image, which is exactly what distinguishes it from finding-level siblings. It enumerates the returned dimensions (cluster, namespace, add-on attribution, CVE counts by severity, risk score, last scan), so an agent knows the shape of the result without opening a schema.

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 an explicit selecting scenario ("which workload should we patch first") and notes it takes the same filters as list_security_findings, which helps an agent pick between the workload-level and finding-level views. It stops short of stating when NOT to use it or naming list_security_findings/list_security_pods as the alternative to prefer for other questions.

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