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 does disclose what the log contains (tool calls, blocked tools, allowed/blocked egress, connects with granted capabilities), but it says nothing about read-only-ness being guaranteed, retention limits, or pagination behavior beyond the schema's limit field.

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 core purpose and followed by the one actionable flag. The parenthetical event list is dense but every element maps to real event types, so little is wasted, though the em-dash construction makes it slightly heavy.

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 tool has four optional params, no annotations, and no output schema, so the description should ideally say more about what a returned audit record looks like or how results are ordered/paginated. It covers the content categories and the key flag but leaves return shape and scope limits to inference.

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 the baseline is 3 and the schema already documents all four parameters. The description's event enumeration largely restates the schema's enum values, adding only a small interpretive nuance ('connects with granted capabilities'), so it does not materially exceed 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 gives a specific verb and resource ('View the safety audit trail') and scopes it as a forensics log of sandboxed server activity versus sandbox blocks, which clearly separates it from siblings like mcp_usage or mcp_sandbox. It never names an alternative sibling explicitly, so the differentiation is implied rather than stated, keeping it below a 5.

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?

Usage guidance is limited to the parameter-level hint 'Use `securityOnly: true` to see only blocks and errors' rather than any when-to-use-this-vs-another-tool statement. An agent can infer this is the forensics/compliance view, but no exclusion or alternative routing is given.

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