system_stats

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

With no annotations present, the description carries the full burden and succeeds: it declares read-only safety, polling friendliness, near-verbatim forwarding, the exact returned device/system fields, and even the secret-bearing argv caveat. It also discloses the routing exception versus other tools.

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?

Every sentence adds operational value: what it reads, what it wraps, exact return fields, when to call it, and routing caveats. The paragraphs are front-loaded with purpose and followed by actionable warnings, with no filler.

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?

Despite no output schema, the description spells out the devices/system response shape and the server_not_running failure mode. It also covers the edge case of COMFYUI_URL/COMFYUI_HOST being set and the need to resolve routing before gating a run, making the tool safely callable in realistic conditions.

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 tool has zero parameters and 100% schema coverage, so parameter-meaning additions are unnecessary; baseline 4 applies. The description uses the space to explain what the response contains rather than parameter semantics.

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?

Description opens with a precise verb and resource ('Read the live local ComfyUI's VRAM per device and system RAM') and names the underlying endpoint (GET /system_stats). It also differentiates itself from sibling run/job tools by explicitly stating it is not diverted by COMFYUI_URL/COMFYUI_HOST.

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?

It gives a direct call trigger ('Call BEFORE a heavy run') and prescribes the fallback action ('if vram_free is short, call free_memory and re-check'). It also states prerequisites (running ComfyUI), error condition (server_not_running), and warns about target-host ambiguity, leaving little room for mis-selection.

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