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

Annotations mark this as a non-read-only but non-destructive, idempotent operation; the description adds real value beyond them by disclosing the cost model (1 credit/day, plus 1 per lookalike event for brand watches) and the API key requirement. It also clarifies the idempotent behavior concretely — re-watching mutates the event-type set rather than creating a duplicate. It does not cover failure modes or whether an existing watch's other settings are preserved.

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?

A single dense paragraph that front-loads the core effect ('get events when ... changes') before listing event kinds, then closes with cost and auth. Every clause carries information, though the long semicolon chain of event types is harder to scan than a short structured list would be.

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 describe return values, and it does cover the mutation semantics, idempotency, cost, and auth that the annotations alone don't. What's missing is how this relates to list_watches/unwatch for lifecycle management, which matters for a subscription-style tool.

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 coverage is 67% and the description compensates by enumerating the watchable entity categories (domain, phone, wallet, brand) that map to the type enum, and by explaining that 'watching it again updates the event types', which gives meaning to the optional events array beyond its schema line. It adds no format detail for value beyond what the schema already says (E.164, wallet address, brand id).

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 names a specific verb (get events) and resource (watches on domains, phones, wallets, brands) and enumerates the event categories, so the agent can distinguish it from snapshot tools like lookup_domain. It never explicitly names a sibling or states the contrast, leaving that inference to the reader.

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?

Usage conditions are implied rather than stated: cost ('1 credit a day'), 'API key required', and the note that 'watching it again updates the event types' tell the agent about operational constraints. There is no explicit guidance on when to choose watch over lookup_domain/list_events, or how it relates to unwatch.

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