zcell_list_anomaly_policies

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

The description reinforces the readOnlyHint annotation with 'Read-only' and details the return shape (one row per policy with the fields listed) and the lookback window behavior. While it echoes the annotation context, it adds value by naming exact output fields beyond the schema, which helps with chaining. It misses on noting pagination behavior (also missing from the schema), but the query params for page/size imply it.

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 three sentences and front-loads the purpose, then context, then chaining—a clear funnel structure. Every sentence adds value. It's arguably the ideal length for a list tool with rich annotations, as it reiterates the read-only nature and gives actionable details without bloat.

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?

For a list tool with an existing output schema (though minimal) and 5 parameters, the description covers the full lifecycle: input (`days`), output fields, and downstream consumption (`id` chaining). The only gap is a canned example showing `days=30` usage or common combinations, but the description already goes further than typical list tools by preemptively warning about the `query` parameter's gotchas. It confidently covers the 'model the agent's mental model' bar.

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?

The `query` parameter description is exceptional—it goes beyond the schema with concrete JMESPath examples, warns about the snake_case/camelCase mismatch, and even provides a troubleshooting tip (call without `query` to see field names). The `days` lookback is documented in the description text. While `policy_type` lacks enum values, the schema provides a title and type, and the description's explicit warning for `query` more than compensates for this small gap.

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 uses a specific verb+resource ('List Zscaler Cellular anomaly policies') and clearly distinguishes this from sibling tools by enumerating the returned fields (id, name, type, enabled state, run status, applied SIM location groups, violation count) and referencing the sibling log and violations tools by name. It's immediately clear this lists policy summaries rather than logs or violations.

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 clear context ('Use the returned `id` with the anomaly-policy logs and violations tools'), which serves as light chaining guidance and implicitly explains when to use this tool vs. relevant siblings. However, it doesn't explicitly state when NOT to use the tool or reference search/alternatives by exact naming beyond the high-level 'anomaly-policy logs and violations tools', which is a minor miss given the sibling list shows many similar tools.

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