audit_logs

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'no state is modified' largely restates structured data. The description adds useful pagination framing via page/per_page, but says nothing about ordering (newest-first?), retention, or whether an empty page signals the end, which are the behaviors an agent actually needs for a read tool.

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 tight sentences with the resource and pagination scope front-loaded and the usage hint immediately after. No filler or redundant phrasing.

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, three-parameter listing tool with no output schema, the definition covers purpose, usage, and safety adequately. The main residual gap is return-shape and ordering guidance (what an audit event contains, newest or oldest first), which would help an agent interpret results.

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%, with page, per_page, and server_id all documented including defaults and the 1-25 cap. The description only echoes that page and per_page control pagination without adding ordering, boundary behavior, or server_id fallback semantics beyond the schema, so baseline 3 applies.

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: 'Read one page of Wisp audit events for a server.' The resource ('audit events' vs. the sibling 'read_log_tail' which implies console/log tailing) is distinct enough that an agent can tell them apart, and the pagination scope is stated up front.

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?

Gives explicit when-to-use guidance: 'Use to investigate recent panel actions or changes.' It does not name a when-not condition or point to the alternative sibling (e.g., read_log_tail for console output), which keeps it from a 5.

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