mcp_audit

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

With no annotations, the description carries the full behavioral burden. It discloses what the log captures and how securityOnly narrows it, but says nothing about read-only semantics, event retention/coverage window, ordering, or what happens when filters match nothing — gaps that matter for a forensics 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 sentences, front-loaded with the resource and its scope, followed by the one actionable filter hint. The parenthetical enumeration is dense but each item earns its place by matching a real event type.

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?

With no output schema, the description usefully describes the returned event content, which is the key missing structured information. It stops short of covering ordering/recency limits or the fact that results are capped, though the limit/ordering details do live in the schema.

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 description coverage is 100%, so all four parameters are already documented, including the securityOnly meaning and the limit default/ordering. The description's securityOnly sentence ('blocks and errors') largely restates 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 ('View the safety audit trail') and immediately scopes it as a forensics log, then enumerates exactly what it contains: tool calls, blocked tools, egress allowed/blocked, connects with granted capabilities. That enumeration maps onto the `event` enum and separates it from analytics-style siblings like mcp_usage.

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?

Explicitly tells the agent when to narrow scope: 'Use `securityOnly: true` to see only blocks and errors.' However, it never says when to reach for this tool rather than alternatives such as mcp_usage or mcp_gateway_health, so selection guidance is clear but not complete.

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