delete_install

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

Annotations already mark it destructive and non-idempotent, but the description adds substantial context beyond them: the exact data destroyed, the fact that completed DoorDash deliveries are unaffected, and the post-condition that the API key stops working and a reuse starts a fresh install.

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?

Four short sentences, each earning its place: scope of deletion, boundary of non-deletion, irreversibility warning, and post-call credential behavior. Front-loaded with the primary effect before the caveats.

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?

With no parameters, no output schema, and safety hints fully covered by annotations, the description supplies everything else an agent needs — side effects, client-confirmation requirement, and consequences for credentials — with nothing material 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?

The tool takes zero parameters, so the baseline is 4; there is no parameter syntax left for the description to clarify. It correctly spends no words restating an empty schema.

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/close) plus the resource and enumerates exactly what is removed: account, usage history, scheduled queue, and uploaded support bundles. It is unmistakably distinct from read-oriented siblings like get_account or list_deliveries.

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 when-to-use context by framing it as a terminal, irreversible action that requires user confirmation before calling. It does not name an alternative recovery/migration path, but for a tear-down tool the exclusions are largely self-evident.

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