zcell_list_audit_customers_search

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

The description explicitly states 'Read-only' and confirms with the readOnlyHint annotation. It also discloses that before/after data blobs are omitted from the rows, which is a behavioral detail not apparent from the schema. No contradictions with annotations.

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 sentences—and clearly structured. It states the primary action, the read-only nature, the output format summary, and the key parameters without unnecessary verbosity.

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?

The description provides a summary of what is returned (who, what, when, operation) and notes the omit of blobs, which is useful given no output schema. It does not mention pagination or error cases, but for a search tool, the core context is adequately covered.

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 is described in the schema (JMESPath). The description mentions 'days' window and 'operation/object/visibility filters', covering days, operation_type, object_id, object_name, object_type, and visibility, but leaves page, size, and modified_by_user_id unexplained. Given 10 optional parameters, the description only partially compensates for the low schema coverage.

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's purpose: searching Zscaler Cellular audit-log entries. It specifies the resource (audit logs), the action (search), and key details (read-only, curated rows, lookback window). This effectively distinguishes it from list-only sibling tools like zcell_list_audit_metadata.

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 explains when to use the tool: for searching audit logs with optional filters (operation/object/visibility) over a specified time window. It also mentions read-only nature and omission of before/after blobs, giving context. However, it does not explicitly contrast with alternative list/search tools, so it's clear but not perfectly proactive.

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