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

Annotations already flag destructiveHint=true and idempotentHint=false, so the safety profile is partly covered. The description goes beyond that by stating irreversibility, specifying exactly what related data is destroyed, and detailing the confirmationToken requirement with the preview-then-confirm sequence. It does not restate the idempotency or openWorld hints, but adds real operational context.

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 dense sentences, no filler. The destructive/irreversible nature and the pause alternative are front-loaded before the procedural confirmation requirement, which matches how an agent should reason about the call.

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?

An output schema exists so return values need not be explained, and the description covers the mutation's scope, irreversibility, alternative, and the required precondition. Minor gap: organizationId/projectId/requestId semantics are absent and must be inferred, but nothing blocks a correct 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 coverage is 0%, so the description must carry the load. It explains confirmationToken semantics (must come from preview_operation with matching tool and arguments) and implies the 100-item cap on trackedQueryIds. organizationId, projectId, and requestId are left unexplained, but the two non-obvious parameters are handled.

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?

States a specific verb (Delete) and resource (tracked queries), plus blast radius (captured answers, matches, metrics history) and a hard cap (up to 100). Clearly distinguishable from update_tracked_queries and delete_cluster among siblings.

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?

Explicitly names the alternative for a non-destructive path (pause with update_tracked_queries) and the condition that selects it. Also spells out the mandatory confirmation workflow via preview_operation, which is the key routing decision an agent must make.

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