Get watcher status

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful context beyond them by disclosing what is inspected (the rules file actually read, the watcher's own RCI session state, last delivery error) and the operational intent of liveness checking. No auth, rate-limit, or failure-mode caveats are given.

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?

Two sentences, purpose front-loaded, and the usage hint placed last. The per-rule field enumeration is dense and slightly list-heavy, but every item is informative given there is no output schema to carry it.

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 no output schema and no parameters, the description carries the full burden of explaining what comes back, and it does so thoroughly — process state, config provenance, session state, and per-rule counters/errors. An agent knows what it will receive and when to call 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool applies. The description instead spends its detail budget on the return contents, which is the right allocation.

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 opens with a specific resource ('background event watcher') and enumerates exactly what the status payload contains: running state, rules file read, RCI session state, and per-rule fields (source, poll interval, cooldown, next-poll seconds, counters, last delivery error). This is far more specific than the title and clearly separates it from siblings like test_watch_rule or get_log.

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?

'Use it to check that a rule is alive without waiting for the event it watches for' gives a concrete trigger and implicitly contrasts with test_watch_rule (which would exercise a rule). It stops short of explicitly naming that alternative or stating when not to use this tool, so it is clear context rather than full routing guidance.

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