health_check

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

With no annotations provided, the description carries full burden. It declares 'Read-only — no mutation' and enumerates exactly what it reports (version, GPU, RAM, queue depth, model populations, recent errors) and where those come from (/internal/logs). It does not detail side effects, but being read-only, none are expected. Could mention performance impact of polling many categories.

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?

Four well-structured sentences: purpose, reported metrics, read-only note, usage guidelines, and contributor credit. Front-loaded with the key purpose. Every sentence adds value; no redundancy or fluff.

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 tool's complexity (multiple health signals), no output schema, and no annotations, the description covers the major return values and use cases. It mentions the specific sources (e.g., /internal/logs, model categories). A slight gap is that it doesn't describe the output format (JSON with specific keys), but for a health diagnostic the agent can infer. Overall, enough for an agent to decide to use it.

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?

Schema coverage is 100%, so baseline is 3. The description adds minimal extra meaning: it restates parameter defaults (model_categories default list, recent_errors default 20) which are already in the schema descriptions. No additional context about parameter edge cases or behavior is provided beyond the schema.

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 it's a 'Pre-flight diagnostic' that aggregates signals for health checking before dispatching. It lists specific metrics reported (version, GPU, RAM, queue depth, model populations, recent errors) and distinguishes itself from sibling tools like get_system_stats or get_queue by being a comprehensive one-call diagnostic.

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 advises use cases: 'when a job fails for an unexpected reason, before a long batch run, or to confirm a remote ComfyUI is healthy.' Also notes it is 'Read-only — no mutation,' helping agents avoid using it for non-diagnostic tasks. However, it does not mention alternative tools for specific checks (e.g., get_system_stats).

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