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

Annotations already flag destructiveHint=true and non-idempotency, and the description adds substantial value on top: it names the collateral data destroyed (answers, matches, metrics), declares the operation irreversible, and documents the confirmationToken gate. This is exactly the extra behavioral context annotations cannot carry.

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, zero filler, front-loaded with the action and blast radius before the alternative and the mandatory workflow. Every clause earns its place.

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 destructive, gated mutation tool with an output schema (so return values need not be described), the definition covers purpose, scope, irreversibility, alternative path, and the token acquisition workflow. Nothing an agent needs in order to call this safely is missing.

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 0%, so the description must compensate. It fully explains the least obvious parameter (confirmationToken: how to obtain it via preview_operation and the user-agreement precondition) and confirms the 100-item cap that matches maxItems. It leaves organizationId, projectId and especially requestId unexplained, which is a real but smaller gap since those names are largely self-describing.

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 the exact blast radius: 'together with their captured answers, matches and metrics history' and the batch limit of 100. An agent can distinguish this from pause_tracked_queries and delete_cluster without opening any schema.

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 provides the when-not and the alternative: 'to stop spending budget without losing history, pause them with pause_tracked_queries instead.' It also spells out the required prerequisite workflow (preview_operation first, show plan, get explicit user agreement) so there is no inference required.

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