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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the remaining burden is scope and shape of results. The description adds the 30-day retention window on closed/fixed items, the cost-based sort order, and the presence of an id per entry — all genuinely behavioral facts not in the annotations. It does not say whether results are capped or paginated, which is the remaining gap.

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, with the population and ordering stated first and the id-based follow-up second. No filler, no restatement of the title, and every clause carries information an agent needs.

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 return-shape burden and does reasonably well: it names the population, ordering, and the id field. It omits other per-alert fields and any result-count or pagination behavior, which keeps it from fully complete for an agent deciding how to consume the output.

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 no parameters, so there is no schema semantics to supplement; baseline is 4. The description correctly implies the fixed scope is not caller-configurable, which prevents an agent from hunting for filter arguments that do not exist.

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?

"Watchdog alerts: open issues, plus those closed or fixed in the last 30 days" states the resource and the exact scope in one clause, and "most expensive first" fixes the ordering. Naming get_alert, get_fix_prompt and mark_fix_done as consumers of the returned id makes the boundary against sibling tools unambiguous.

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?

The description tells the agent precisely what population it receives (open plus recently closed/fixed), which is the main selection decision for a zero-argument tool, and routes follow-up work to three named siblings. It stops short of an explicit negative case (e.g., 'do not call this expecting full history — use get_history'), so it misses the top band.

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