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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds non-obvious context: the call is free, the backend probes roughly every 15 minutes, and next_since should be threaded to the next call. These behavioral details go beyond what the structured fields convey.

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 tight sentences, front-loaded with the free/polling cue and the payload description. It is information-dense without wasted words, though the packed clause listing change types is slightly heavy.

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, the description needn't explain return values, and it still covers cost, cadence, scope, and the pagination handoff. Nothing essential for calling it correctly is missing.

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 description coverage is 100%, so the schema already documents watch_id, since, and limit. The description reinforces the since/next_since pagination pattern but adds no syntax or format detail beyond what the schema provides; baseline 3 is appropriate.

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 states a specific resource and scope: everything a Watchdog has recorded for its endpoint since an alert id, listing the change types (status, payability, price, payTo). It clearly differs from sibling reads, but it never contrasts itself with a named alternative such as settled_check or settled_status, so it stops short of full sibling differentiation.

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?

"Poll it whenever your agent runs; the endpoint is probed about every 15 minutes" gives concrete when-to-use and cadence guidance tied to the 15-minute probe cycle. It lacks any explicit when-not-to-use or alternative-tool routing, but the operating context is clear.

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