io_stats

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the PCAP is scanned only on the first call per (interval, filter) combination, with subsequent pages served from cache. This is a useful behavioral trait. It does not explicitly state that the tool is read-only, but the context implies no modification. Overall, good transparency.

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 extremely concise: four sentences, each adding value. It is front-loaded with the core purpose, followed by paging and caching behavior, then default and special values. No redundant or unnecessary information.

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?

Given the complexity (5 parameters, no output schema, no annotations), the description covers the main usage patterns: pagination, caching, interval meaning. However, it does not detail the return format (e.g., whether each interval includes frame count and byte count as separate fields) or the behavior of the 'display_filter' parameter. This is a minor omission for a tool that is primarily about reading data.

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 schema has 0% description coverage, so the description must compensate. It explains that 'interval_ms' is the bucket size, and that 'skip'/'limit' control paging, with the default limit and special value (0) documented. However, the required parameter 'alias' and 'display_filter' are not explained at all, leaving gaps in semantic understanding.

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 begins with 'Per-interval frame and byte counts,' which clearly states the tool's function: it provides counts of frames and bytes aggregated over time intervals. This distinguishes it from sibling tools like iograph (which likely deals with I/O graphs) and protocol_stats (which probably concerns protocol-specific statistics).

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 explains pagination with skip/limit and caching behavior (first call scans, subsequent pages from cache). It also mentions the default limit and how to get all results. However, it does not provide guidance on when to use this tool versus alternatives such as iograph or protocol_stats, nor does it specify prerequisites or exclusions.

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