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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety bar is lower, but the description still adds real value by concretizing the blast radius ("can restart or scale services") and imposing a confirmation gate. It stops short of stating reversibility, idempotency, or failure behavior for a destructive operation, so not a 5.

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 short sentences, front-loaded with the action, then the danger, then the precondition and parameter sourcing. No sentence is 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?

Covers action, risk, gating, and parameter provenance for a two-param destructive tool with no output schema. The remaining gap is what an execution returns (status, logs, failure modes), which the agent would otherwise have to discover empirically.

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 0% for both params, so the description must carry the load. It usefully explains the provenance of runbookId (from the diagnosis recommendation or candidate list) but says nothing about incidentId or the accepted ID format; incidentId is inferable from context only.

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?

Specific verb+resource: "Execute one specific runbook against an incident." The 'one specific' qualifier distinguishes it from bulk/listing siblings and frames the unit of action unambiguously.

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?

Explicit gating: only after diagnose_incident recommended it AND user confirmation, naming the sibling tool that produces the prerequisite. It also tells the agent where the runbookId comes from (the diagnosis's recommendation or candidate list), removing the main source of mis-invocation.

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