get_audit_logs

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

With no annotations provided, the description carries the full burden. It explicitly states the tool is read-only and that it is fatal if the chosen source is unavailable, which warns about error conditions. It does not mention permissions or output formatting, but the output schema likely covers return values, so the description adds meaningful behavioral context beyond the basic operation.

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, front-loaded with the core purpose, followed by parameter defaults and usage guidance. Every sentence adds distinct value, and the alternative tool is mentioned efficiently. No fluff or 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?

For a simple read-only tool with two simple parameters and an output schema, the description is complete. It covers purpose, sources, parameter defaults, error behavior, and use cases, while also pointing to a sibling tool for related needs. The output schema handles return-value details, so no additional explanation is required.

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 coverage is 100%: both parameters (lines and source) have descriptions specifying defaults and allowed values. The description restates the same information ('source param: journalctl, audit.log, or auto (default). lines defaults to 50') without adding new semantic depth, so it provides no added value beyond 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?

The description clearly states the tool returns kernel audit events from specific sources (journalctl -k or /var/log/audit/audit.log) with examples of event types (AVC denials, system calls). It explicitly distinguishes from sibling tool get_failed_logins by directing users to that tool for login attempts.

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 usage context ('Use for security forensics') and an explicit alternative ('get_failed_logins for login attempts'). It also cautions about fatal behavior when the source is unavailable, which helps agents decide when to use this tool.

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