rule_stats

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

The '[READ]' annotation-like prefix signals a non-destructive operation, and 'busiest first (top-N)' discloses the sort order. With no annotations provided, the description carries the full burden, and it does reasonably convey it's a read operation. However, it doesn't disclose whether this reflects a rolling window, sampled counts, or cumulative totals, nor what happens when the target is invalid.

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?

The description is compact and well-structured: a one-line summary followed by an Arg block. No redundant verbiage. It earns its place but is slightly terse on edge cases.

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 top-N read tool with only 2 optional parameters and no output schema, the description covers the essentials: what it returns, sort order, and parameter semantics. It's adequate for a simple reporting tool. Could be more complete with return-format hints, but the simplicity keeps it at a healthy baseline.

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?

The description briefly explains both parameters inline: 'top' is how many rules to return (busiest first) and 'target' is the firewall target name with a fallback to default. With 0% schema description coverage this is helpful context, though it could add value-type clarification (e.g., top accepts only positive integers) and does not fully compensate for the caller's uncertainty around target name formats.

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 clearly states 'Per-rule hit counts / evaluations, busiest first (top-N)' with a specific verb+resource+scoping. It's distinguishable from siblings like rule_detail and rule_states since it focuses on hit counts/usage frequency. Slight deduction because it doesn't explicitly contrast against these sibling tools.

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?

The description implies read-only usage ('[READ]' prefix and 'counts'), which helps distinguish from mutation tools like toggle_rule or reconfigure. However, it doesn't explicitly state when to use this tool vs. the closely related rule_states or rule_hit_and_shadow_analysis, and provides no exclusion guidance.

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