audit_tail

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

With no annotations, the description carries the burden; it does disclose the output encoding (JSON lines) and the auditing-enabled precondition, which are useful. However, it never says what happens when auditing is disabled (error vs empty result) or whether the read is bounded, leaving real behavioral gaps.

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?

A single front-loaded sentence with no waste; the format and precondition are packed in efficiently. Brevity is close to the limit of usefulness rather than verbose.

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?

An output schema exists, so return structure needn't be explained, and the description covers the basic purpose and precondition. But for a log-reading tool it omits the 'lines' parameter and the disabled-auditing behavior, so an agent still has open questions.

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 0% and the single 'lines' parameter (default 20) is never mentioned. Its name is fairly intuitive, but the description adds no meaning about count semantics, maximums, or ordering beyond the vague 'most recent'.

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 ('Return the most recent audit log entries') and adds the output format ('JSON lines'). This distinguishes it reasonably from neighbors like read_event_logs or git_log, though it never explicitly names a sibling.

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?

There is no when-to-use guidance and no named alternative. The clause 'if auditing is enabled' is a precondition, not usage guidance, and the agent is left to infer when to reach for audit_tail over read_event_logs.

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