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

No annotations provided, so description carries full burden. It clearly indicates a read-only operation (retrieving history) and lists return fields (impact level, start time, resolution/duration, uptime percentage, incident count). No side effects or contradictions.

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 concise sentences with no waste. The first sentence defines the core function and return data; the second provides usage examples and additional return info. Efficiently structured.

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?

Given one simple parameter and no output schema, the description covers the key aspects: what it retrieves (history), scope (30 days), and return fields. Lacks explicit differentiation from siblings and does not mention authentication requirements, but overall sufficient.

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 100% for the single required parameter. The description adds minimal meaning beyond the schema, essentially repeating the schema's description of the 'service' parameter. Baseline 3 is appropriate.

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 clearly states the tool retrieves recent incident history (last 30 days) for a specific AI service, specifying details like impact level, start time, and resolution/duration. It distinguishes itself from siblings: 'check_ai_status' presumably gives current status, 'list_ai_services' lists services, while this tool provides historical data.

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 provides example queries ('has Anthropic been reliable lately?') indicating appropriate use cases. However, it does not explicitly state when not to use this tool or mention alternatives like 'check_ai_status' for current status.

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