Return recent browser command audit entries with action, JS-stripped params, success status, error, and duration; filter by limit or time to review what the agent did.
Return recent command audit entries: action, params (JS code stripped), success flag, error, duration. Useful for "what did the agent do?" reviews.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| since_ms | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does add genuinely useful behavioral detail: the entries are recent command-level records and JS code is stripped from params before being returned (a meaningful data-handling trait an agent should know). It does not cover ordering, retention window, or any auth/permission requirement for reading the audit trail, so it remains partial.
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 no filler. The return-field enumeration is front-loaded and the use case follows, so nothing needs to be re-read.
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?
Because there is no output schema, the description usefully enumerates the returned fields, which covers the return-value gap. But a query tool with two undocumented filtering parameters and no annotations still leaves the agent guessing about the time-window semantics, which is the one thing needed to call it correctly.
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 0% and neither of the two parameters is mentioned in the description. The agent gets no explanation of what limit caps or how since_ms is interpreted (epoch milliseconds vs. relative offset), even though the defaults (100, 0) imply a filtered-window query. The description 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?
The description names a specific verb+resource ("Return recent command audit entries") and enumerates the returned fields, so the agent knows exactly what this produces. It does not explicitly differentiate from nearby siblings like browser_logs or browser_console_logs, which could plausibly be confused with an audit log, so it stops short of 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?
"Useful for 'what did the agent do?' reviews" gives an implied use case, which is real guidance. However, it never states when NOT to use it or points to the alternative tools (browser_logs, browser_console_logs) for related diagnostic needs, leaving the selection decision to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.