get_audit_logs

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

Annotations already declare readOnlyHint=true, so the read-only nature is known. The description adds value by explaining the log is persistent and on-disk, and that it captures all write operations across sessions. No behavioral contradictions.

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?

Two sentences, efficiently conveying purpose, usage, and differentiation. No redundant information.

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 tool's simplicity (read with pagination, no output schema, annotations present), the description covers the core behavior and context. Could mention sorting or entry format, but not essential.

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 has 2 parameters (limit, offset) with 50% description coverage (offset has a description, limit does not). The tool description adds no additional parameter meaning beyond the schema, failing to compensate for the low coverage. This leaves the agent without clarity on the limit parameter.

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 it returns recent entries from the persistent on-disk audit log of all write operations. It specifies the resource (audit log) and the verb (return), and distinguishes from the sibling get_logs tool by noting it covers across sessions vs. in-session debugging.

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 explicitly states when to use this tool ('Use to review what mutations ... across sessions') and when to prefer an alternative ('Prefer get_logs for debugging in-session behavior and transient connection errors'). This provides clear guidance on tool selection.

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