audit_tail

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

The description declares 'Read-only — no side effects', explains error behavior when the log file cannot be read, and details the default and maximum for n. There are no annotations to contradict, so the description fully covers behavioral traits.

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, with each sentence serving a distinct purpose: action, safety, error handling, parameter guidance, and sibling differentiation. No redundant words.

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?

The description covers the return format ({ok:true, entries:[...], count}), error case, parameter details with defaults and cap, and usage context. For a simple tool with one parameter and no output schema, it is fully complete.

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 already describes the parameter n with default and max. The description adds usage context: 'use a larger value only when debugging a busy system', which provides additional semantic guidance 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 'Return the N most recent audit log entries in ascending timestamp order', specifying the verb (Return), the resource (audit log entries), and ordering details. It distinguishes itself from the sibling tool audit_query by mentioning filtering capabilities.

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 vs. audit_query: 'Prefer audit_query for filtered searches... use this tool for real-time monitoring or quick post-action verification'. It also provides guidance on the default value and cap for the n parameter.

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