Show audit log

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description usefully adds that entries carry an outcome classification (allowed/denied/awaiting approval) rather than raw events, but says nothing about ordering, retention window, or whether the log is scoped to the calling agent or the whole workspace. With annotations carrying the main burden, a 3 is fair.

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 zero filler; the operative noun and the returned content both land immediately. It is efficient, though the brevity leaves the gaps noted in other dimensions unfilled.

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 optional-parameter read tool with a safe annotation profile and no output schema, the description covers what the tool is and roughly what comes back. It stops short of the details an agent would want before invoking: result ordering, the scope of the log, and the effect of the limit parameter.

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?

One parameter at 0% schema description coverage: the schema gives bounds and a default (1-100, default 20) but no narrative meaning. The description only obliquely implies recency ordering via 'most recent' and never explains what limit controls or what happens when it is omitted. It does not compensate for the coverage gap.

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?

Specific verb plus resource ('Show' + 'audit log'), and it goes beyond the title by naming the payload contents: recent tool calls with their allow/deny/pending-approval disposition. It does not distinguish itself from the nearest sibling, guard_get_policy, so an agent must infer that one covers policy and the other covers call outcomes.

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 statement of when to reach for this tool versus guard_get_policy, who can see the log, or whether it is a privileged inspection surface. Usage is only implied by the phrase 'most recent tool calls'.

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