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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real substance beyond them: the deletion is irreversible, it cascades to the template report, external Drive/OneDrive files survive, ownership is required, and from an AI client the call returns `confirmation-required` and completes only after user confirmation in Rollstack. That last detail is behavior an agent cannot get from any structured field and directly affects retry/loop handling.

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?

Front-loaded with the destructive scope, then consequences, then permissions, then the confirmation flow. Every sentence carries information, though the template-explanation clause is slightly verbose and the fragmented "Only the burst's owner may." reads as an incomplete sentence.

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, cascading operation with no output schema, the description covers everything an agent needs to act correctly: what is destroyed, what is preserved, who may call it, and why the call may return without doing the work. The only omission is how the idempotency key interacts with the confirmation step, which is minor given the schema documents the key itself.

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 50%, and the description adds no meaning about either parameter: `id` is documented only in the schema (including where to copy it from), and `idempotencyKey` is never mentioned in the description despite the call being destructive and gated behind a confirmation step where retries are likely. Adequate but leaves a real gap around safe retry semantics.

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?

Opens with a specific verb and resource ("Deletes a burst") and immediately bounds the scope: every report in the burst plus the template report it was made from. This is materially more precise than the sibling delete tools, which target configs, datasets, memories, or templates rather than a burst tree.

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?

Gives a prerequisite ("Only the burst's owner may") and explains the confirmation gate that applies specifically to AI clients, so an agent knows the call may not complete synchronously. It does not name an alternative for the near-miss case (deleting only the template or only the reports), leaving that inference to the agent.

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