event_list

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

The description adds behavioral context beyond the annotations by stating 'newest first' ordering, pagination, return item fields, and the target config source. Annotations already cover read-only/destructive/idempotent safety, so the added details are useful and non-contradictory.

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 front-loaded with '[READ]' and a concise summary, followed by a short field list and a structured args block. Every sentence contributes useful information without redundancy or 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?

Given the absence of an output schema, the description compensates by enumerating returned item fields. It covers ordering, filtering, pagination, and usage context. Annotations handle the safety profile, leaving no significant gaps 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?

With 0% schema coverage, the description fully compensates by explaining each parameter: severity with examples (ERROR, WARNING, AUDIT_FAIL), limit as page size with default, offset as page offset, and target as coming from config.yaml. This adds semantic meaning far beyond the bare property definitions.

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?

Clearly states 'List Horizon audit events (newest first), optionally filtered by severity,' with a specific verb and resource. Distinguishes from sibling tools like session_list and machine_list by focusing on audit events and explicitly connecting to 'what went wrong recently.'

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?

Provides a direct use case: 'Use for "what went wrong recently".' This clarifies when to invoke the tool, though it does not explicitly name alternative tools or exclusion criteria. Given that no sibling tool covers audit events, the guidance is sufficient.

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