generate_compliance_report

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

With no annotations provided, the description carries the full burden. It discloses that this is a write operation recorded in the audit log and that generation is asynchronous. This adds significant behavioral context beyond the basic trigger action, though it could also mention idempotency or potential errors.

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 (~120 words) and well-structured. It opens with a clear purpose statement, follows with key behavioral notes (async, write operation), and ends with parameter details in an Args block. Every sentence adds value without redundancy.

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?

Given the lack of output schema and annotations, the description covers the essential aspects: asynchronous behavior, parameter semantics, and polling instruction. It does not address error handling, rate limits, or what happens on invalid input. However, it references a sibling tool (get_compliance_report) for status polling, which aids agent understanding.

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 input schema only provides parameter names and types (string). The description adds critical semantic detail: valid values for report_type ('soc2', 'gdpr', 'hipaa') and the exact format for period (e.g., '2026-Q1', '2026-05', '2026'). This compensates entirely for the 0% schema description 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 action ('trigger generation'), the resource ('compliance report'), and the method ('by analysing the audit log'). It also distinguishes from sibling tools by noting the asynchronous nature and the need to poll get_compliance_report.

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 explicit guidance: the tool returns immediately with a pending report, and the agent should poll get_compliance_report until ready. It mentions dependence on audit log volume for generation time, implying variable latency. However, it does not explicitly state when not to use this tool or mention alternatives like list_compliance_reports.

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