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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that: results are newest-first, log_id switches to a single call with request/response excerpts, and secrets are redacted. It does not discuss retention windows or pagination beyond the limit cap.

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 short sentences, front-loaded with what is returned and followed by the detail-mode and trigger. Nearly every clause earns its place; only "Use it when a tool fails" is thin enough to feel like filler.

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 usefully lists the returned fields and notes redaction, which is the key completeness need here. Minor gaps remain around whether log_id overrides the other filters and how the filters combine, but an agent has enough 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 coverage is only 20% (just the limit default), so the description must carry weight and it partially does: log_id is explained as the single-call detail mode, and the field list implies the tool/outcome filters. However, gateway_id and the exact filter semantics of tool and outcome are left to inference.

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 names the specific resource (recent calls to the gateway) and enumerates the returned fields — tool, outcome, HTTP status, error, time — plus the log_id variant. It is clear what the tool does, though it never distinguishes itself from the similarly named list_gateway_issues sibling.

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?

There is one explicit trigger: "Use it when a tool fails." That is real guidance but narrow — it does not say when to prefer this over list_gateway_issues or other diagnostics, nor when not to use it. Usage is otherwise implied by the field list.

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