zia_list_cloud_app_policy

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

Annotations declare readOnlyHint=true, so the agent knows this is a safe read operation. The description doesn't add behavioral details like pagination defaults, whether group_results changes response shape, or what app_class filtering does beyond the parameter name. With readOnlyHint already provided, a 3 is appropriate – the description adds the scope ('policy-engine catalog') but lacks deeper behavioral context like response format or limit behavior.

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 main description is a single concise sentence that efficiently conveys purpose. The schema description for 'query' is verbose but earns its place with actionable warnings and usage examples. No fluff or redundancy. The tool description itself is minimal, and the param description is rich without being bloated.

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 6 optional parameters and no output schema, the description leaves a lot unexplained (pagination behavior, what group_results does, app_class allowed values). However, the excellent query param documentation compensates for some gaps, and readOnlyHint covers the safety profile. Schema coverage is low at 17%, but the query param semantics are so well documented that the overall tool is reasonably complete for an experienced agent. Still, the 5 other params lack any description, so it's not a 5.

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?

Only the 'query' parameter has an in-schema description (17% coverage), but that description is exceptionally detailed and provides critical semantics: JMESPath usage, field-name casing warnings, and a concrete tip to call without query first. The remaining 5 parameters (page, search, app_class, page_size, group_results) are undocumented, and the description adds no extra meaning for them. However, the query parameter alone carries significant value, pushing this above baseline. For the undocumented params, the description should have provided more guidance, but the query doc is a strong asset.

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 'List the ZIA policy-engine cloud-application catalog (Cloud App Control)' clearly identifies the resource (cloud-application catalog) and action (list), and the parenthetical 'Cloud App Control' provides domain context. It distinguishes from siblings that list rules (e.g., zia_list_cloud_app_control_rules) or actions (zia_list_cloud_app_control_actions). A minor gap: it's not explicit about whether this returns the full catalog vs. pageable subset, but the verb+resource is clear.

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 mentions it's a catalog listing, which implies it's for browsing available cloud apps before creating policy rules, but it doesn't explicitly state when to use this vs. sibling tools like zia_list_cloud_app_control_rules or zia_get_cloud_app_control_rule. The purpose is clear enough to infer usage, but there's no explicit when/when-not guidance. The schema's detailed query parameter hints at filtering use cases, but the description itself doesn't provide this guidance.

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