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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: zero cost, a 30-second polling floor, and an auth constraint that only the utility account key can read the records with no public sharing. Error behavior and what an invalid/expired key returns are left unstated.

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 tight sentences with the two usage modes front-loaded, followed by cost, pagination, rate-limit, and auth notes. Every sentence adds a distinct operational fact and none is filler.

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 described, and the description covers purpose, modes, cost, pagination, polling cadence, and auth scope. The only gap is the meaning of watch_id=null versus a populated value and how this read tool relates to the sibling watch-management tools.

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 0% (only bare titles), so the description carries the burden and largely does: it ties the after parameter to next_cursor for pagination and frames the watch_id read path and the api_key as the utility account credential. It never names watch_id explicitly nor explains that its null default selects the list mode, so some syntax remains implicit.

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?

States a concrete verb and resource ('List your private watches, or read one watch's recent results and transition events') and captures both operating modes (list-all vs single-watch read) in one sentence. The resource 'diagnostic watch' cleanly separates it from sibling tools like read_callback_events and read_liveness_events, so an agent can select it without opening a schema.

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?

Gives clear operative context: reads are free, use the cursor by persisting next_cursor as after, and poll no faster than every 30 seconds. It does not explicitly say when to prefer this over related read tools (read_callback_events, read_liveness_events) or when not to call it, so it stops short of full routing guidance.

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