Read persisted structured debug events

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: newest-first ordering, cursor pagination, filterability by correlationId/level/event/operation/time, and the fact that credentials are redacted before persistence. This is meaningful additional context that helps the agent understand what to expect.

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 its place. The first sentence front-loads the core behavior (newest-first, filterable, paginated). The second sentence gives the primary use case (correlationId from consult). The third sentence adds a security-relevant detail (credential redaction). No wasted words.

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 read-only, idempotent, non-destructive tool with no output schema, the description covers the essential context: what events are, how to filter, how pagination works, and the key use case. The only minor gap is that it doesn't explicitly state the return format (e.g., JSON array of event objects), but with no output schema and a clear description of the event types, this is a small omission. The description is complete enough for an agent to call it correctly.

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 only 14%, so the description must compensate. It does: it names the filterable fields (correlationId, level, event, operation, time) and explains the correlationId's purpose ('pass it here to see exactly what happened per model'). It also mentions cursor pagination, which maps to the cursor parameter. However, it doesn't explain the 'since' parameter's format beyond what the schema says, and it doesn't detail the 'limit' parameter's behavior. Still, the description adds significant meaning beyond the sparse schema.

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 verb ('Read'), a resource ('persisted structured debug events'), and the exact content ('dispatches, per-model failures and validation errors'). It also names the sibling it is not (consult) by explaining that consult results carry a correlationId that can be passed here. This clearly distinguishes it from the sibling tools.

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 explicitly tells the agent when to use this tool: after a consult result, pass the correlationId to see exactly what happened per model. It also implies the alternative (consult) by saying 'Every consult result carries a correlationId: pass it here...' This is clear context with an explicit routing condition.

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