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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description's real contribution is enumerating the returned payload — status values, uptime windows, incident/notification history — which matters because no output schema exists. It does not mention limits, empty-state behavior, or authentication needs.

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?

One dense sentence with zero filler, and the subject ('Your watched URLs') is front-loaded. The colon-list style reads as a fragment rather than a sentence, but no clause 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 must carry the return-shape burden, and it does so reasonably well by naming each field family. Parameters are fully covered by the schema. Only minor gaps remain: what an empty watch list looks like and how much incident history is returned.

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%: instance_id is documented as coming from buy or list_utilities, and passport_token is documented as a headerless-auth fallback. The description adds nothing about either parameter, so the baseline 3 applies.

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 concretely what the tool surfaces for each watched URL: status (with the enum values unknown/up/down), last results, uptime percentages over 24h and 7d, and incidents. That lets an agent tell it apart from the mutating siblings uptime_add and uptime_remove. It stops short of explicitly naming those siblings or saying 'read-only view'.

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?

There is no statement of when to call this versus the alternatives (uptime_add to start watching, uptime_remove to stop, heartbeat_status for a different monitoring domain). No prerequisites such as 'the instance must have watched URLs added first' are mentioned, leaving the agent to infer the workflow.

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