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

Annotations already declare readOnlyHint and idempotentHint, and the description adds valuable behavioral context: it always returns coverage alongside uptime, returns 'insufficient_data' when coverage is too low, and clarifies that DigitalPublic publishes no contractual SLA. These are meaningful details beyond the annotations and schema.

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 sentences, each earning their place: the core result, the critical caveat about coverage, and the edge-case behavior. The main function is front-loaded and no words are 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?

For a simple read-only tool with two self-explanatory parameters and an output schema, the description is nearly complete. It covers the main behavior, the mandatory pairing with coverage, the insufficient-data edge case, and the SLA stance. The main gap is explicit parameter guidance, but the enum values and output schema compensate.

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 does little to explain the parameters. It mentions 'component' and 'historical uptime,' which loosely maps to componentId and window, but it does not explain the window options, defaults, or what componentId refers to beyond the name.

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 a specific action ('Return historical uptime') on a specific resource ('a component') and adds the distinctive requirement that data coverage is always included. It is clearly not a status or offer tool, though it does not explicitly name a sibling for contrast.

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?

The description implies when to use the tool: whenever historical uptime for a component is needed, and it warns that coverage must be considered alongside uptime. It does not explicitly mention alternatives like get_service_status or state when not to use it, though the 'no contractual SLA' note suggests it should not be used for SLA verification.

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