system_stats

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

No annotations provided; description fully carries behavioral disclosure. 'Report' implies read-only, no side effects mentioned. Transparent enough for a monitoring tool.

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?

Single sentence, front-loaded, no wasted words. Highly concise and structured.

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?

Has output schema (unknown richness). Description covers purpose and usage scenarios completely for a simple stat reporter. Could add more detail on output format but not necessary.

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?

No parameters; description adds no param info beyond schema, but baseline for 0 params is 4. Schema coverage is 100%, so no 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?

Clearly states it reports device/VRAM usage, provides specific use cases (tuning resolution/batch, after OOM). Distinguishes from 30+ sibling tools as the only system stats reporter.

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?

Explicitly mentions when to use (tuning, after OOM), giving clear context. No explicit when-not-to-use or alternatives, but context is sufficient for the tool's scope.

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