diagnose_check

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

With no annotations provided, the description carries the behavioral burden. It is transparent that the call is read-oriented ('Return') and specifies the returned categories, including that it aggregates results across regions and incidents in one call. It could add notes about costs, permissions, or null behavior, but it clearly communicates the primary non-destructive behavior.

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 sentences, front-loaded with the action and the resource, with no filler. The usage guidance is included in the second sentence without repeating schema details.

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?

There is no output schema, so the description compensates by listing the returned data categories and gives a clear invocation context. It is slightly incomplete in not describing the exact shape/nullability of the returned incident fields, but this is a minor gap for an operator-facing diagnostic call.

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 baseline is 3 regardless of description-level parameter detail. The description adds context by tying recentResultsLimit to 'recent raw results across regions', but it does not add meaning beyond what the schema already states.

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 uses a specific verb ('Return') and a clear resource ('a single check's current state'), then enumerates exactly what is included: status, raw results, active incident, and most recent resolved incident. It also distinguishes itself from chaining list_results + list_incidents, so an agent can tell it apart from sibling tools without opening schemas.

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?

It gives an explicit trigger condition ('when a human asks "what's wrong with check X?"') and explicitly names the alternative to avoid (chaining list_results + list_incidents). This is strong when-to-use guidance with a named alternative.

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