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

Annotations already carry readOnly/idempotent/non-destructive, but the description adds genuinely new context: it is free, needs no account, and requires inputs to be public and non-personal. It also discloses the shape of the result, which the annotations do not.

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?

Three tight sentences with the trigger front-loaded and the return payload second. 'Read-only' is restated even though annotations cover it, a small redundancy, but nothing else is wasted.

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, the description usefully summarizes return fields and auth requirements, and the nested continuity_handle is documented in the schema. It is close to complete; pagination/ordering of the returned events is left unstated.

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 limit, watch_id, and continuity_handle. The description only reinforces the continuity_handle's ownership role ('proves you own these watches'), adding marginal meaning over the schema.

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 specific verb+resource ('Read watch change events') and enumerates what comes back (verdict before/after, change summary, receipt and webhook delivery status). It implicitly separates itself from gaip_watch_list and gaip_watch_register, but never names the alternative explicitly, so a sibling-aware agent still has to infer the boundary.

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 this when asked what changed on a watched agent or service' gives a clear triggering context, and it tells the caller to pass continuity_handle and optionally watch_id. It stops short of naming when NOT to use it (e.g., listing watches vs. reading events).

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