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

Annotations already declare destructiveHint=true, and the description adds meaningful context: deletion is permanent, cascades to every answer, and signed-off runs are refused. This goes beyond the hint by describing the refusal rule and the lack of recovery, though it omits minor operational details such as permission requirements.

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, each carrying distinct information: deletion scope, refusal condition, and the safer alternative action. There is no filler and no repetition of schema details.

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 two-parameter destructive delete with a forced confirm flag, the description plus schema and annotations cover the action, its irrevocability, cascade behavior, and an important edge case (signed-off runs). No output schema is present and none is required.

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 100%, so both 'run' and 'confirm' are fully documented in structured form. The description adds context about the irreversible scope of deletion, but it does not need to re-describe the parameters since the schema already carries that burden.

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 destructive verb and resource ('Delete a run for good, with every answer on it'), and clarifies the scope of deletion includes all answers. It differentiates from ordinary run operations by explicitly refusing signed-off runs, making it distinct from run_sign_off and other run-related 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?

Gives clear guidance: use deletion for runs no longer wanted, but do not delete a signed-off run and abandon it instead. The alternative is described as 'abandon' rather than naming a specific sibling tool, so the referral is slightly implicit.

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