Proxy status

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

Annotations already cover readOnly, idempotent, openWorld and non-destructive, so the safety profile is free; the description adds real context beyond that — one GET to /guardian/stats and a '3 s' latency hint, plus the fields returned. The '3 s' figure is ambiguous (timeout? typical latency? polling interval?), which keeps it from a 5.

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?

It is short and front-loaded, but written in clipped fragments ('window, budget, compactions, tokens saved') that read as an unlabeled field dump rather than explanatory prose. The closing 'Returns those stats.' repeats the earlier list and earns no place.

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?

With an output schema present, return values need not be explained, and the annotations carry the safety profile; the description supplies purpose, sibling routing, endpoint and latency. Only the ambiguous '3 s' and the missing 'when to call this' cue leave minor gaps.

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 takes zero parameters, and the schema is closed (additionalProperties: false) with 100% coverage, so there is nothing for the description to clarify. Baseline 4 applies for a no-parameter tool.

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 names the resource (proxy/guardian stats) and enumerates the reported fields: window, budget, compactions, tokens saved. It clearly distinguishes itself from the span-reading siblings. The clipped, question-style opening ('Proxy up and compacting?') makes the core purpose slightly less crisp than a clean verb+resource statement.

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 explicitly routes the agent away: 'Use list_spans, search_spans or read_span for archived conversation text', naming all three siblings and the condition that selects them. It implies this tool is for proxy/compaction status but never states when to call it (e.g., health checks, budget questions) as directly as the exclusion is stated.

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