audit_history

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the limit default (50) and cap (500), and clarifies that summary_only changes the return shape to per-session aggregates, but says nothing about read-only nature, permissions, ordering, or pagination.

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?

One front-loaded summary sentence followed by a compact per-argument list — no filler, and each line earns its place given the 0% schema coverage. The structure is appropriate to the parameter count, though slightly list-heavy rather than prose-efficient.

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 7-parameter query tool with no annotations and an existing output schema, the description covers all inputs and the key output-shape switch (summary_only). The remaining gaps — ordering, permissions, pagination — are minor given the output schema exists.

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?

Schema description coverage is 0%, so the description must carry the full load, and it does: all seven parameters are documented with meaning, and the event_type and status_filter parameters are given concrete enum values (tool_call, waapi_call, tcp_command, session_start, session_end; ok, error) that exist nowhere in the schema.

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?

States a specific verb and resource — 'Query past session log events' — with the filtering scope made explicit. It is clear and distinguishable from most siblings, though it does not differentiate itself from the closely related audit_session_stats sibling, which its own summary_only parameter arguably overlaps with.

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 filter list implies the use case (retrieving/filtering historical events), and the summary_only note hints at an aggregate mode. However, there is no explicit when-to-use guidance and no routing against audit_session_stats, which appears to serve a similar aggregate purpose.

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