system_stats

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

The main description says 'Return', suggesting read-only behavior, but the reset parameter can mutate operation metrics. The input schema describes this reset behavior, but the tool-level description does not call out the side effect or clarify whether stats are cumulative or resettable.

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 short, focused, and front-loads the main purpose before listing included statistics. Every sentence contributes useful information without redundancy.

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 statistics tool, the description lists categories but omits details about return format, units, whether metrics are cumulative/current, and the exact effect of reset on subsequent calls. The reset parameter is explained, but an agent would need more context to fully interpret the response.

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 single reset parameter is fully described in the schema with a default value, so parameter coverage is complete. The tool description does not add extra meaning about the parameter beyond what the schema already provides, so it meets the baseline but not more.

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 the tool returns measured operation and subsystem statistics and enumerates the included categories (latency, cache counters, catalog totals, vector-index stats). It is less specific than some sibling tools like vector_index_status or vault_stats, but the name and scope make the primary purpose clear.

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 this is the tool for system/performance metrics rather than content or graph statistics, but it does not explicitly state when to choose it over sibling tools such as vault_stats or vector_index_status. There is no explicit alternative guidance.

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