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

Annotations already cover readOnlyHint and openWorldHint, so safety is handled. The description still adds real value by disclosing the embedded payload — a bounded window of the 10 most recent health checks with their fields — which tells the agent what evidence it will get without a second call.

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 with no waste: the return payload first, the usage trigger second. Every clause carries information an agent needs.

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 does the work of describing return content, and it does so adequately. The only real hole is how to construct the serviceId, which nothing else in the definition covers.

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% and the description never explains what a serviceId is — whether it is a numeric ID, a slug, or a service name, or where to obtain it. With a required identifier as the sole parameter, the description leaves the agent guessing at the one thing it must supply.

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 and resource ('Get one service's details') and enumerates what comes back (10 most recent health checks with status codes, latency, errors). The 'one service' phrasing implicitly separates it from list_services, though no sibling is named.

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 a clear triggering context: 'Call this when diagnosing WHY a service is degraded or down.' It does not state when NOT to use it or mention the adjacent diagnose_incident tool, so the routing is only partially pinned down.

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