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

With no annotations, the description carries the full behavioral burden. It clearly discloses the mutating nature (destroy) and adds a useful security trait ('key passes through and is never stored'), but it does not state irreversibility, billing effects, or failure behavior.

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?

Two short sentences with no filler; the action is front-loaded and the security note is a single additional clause.

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 simple three-parameter destructive action, it covers the action, target, provider options, and key-handling behavior. It omits response/confirmation details, but no output schema exists and an agent can still invoke the tool correctly.

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?

Most parameter meaning is left to field names; however, the description adds the allowed provider scope (vast or runpod) and clarifies that api_key is passed through rather than stored. It does not explain how to obtain provider_instance_id, so compensation is partial.

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 clear destructive action ('Destroy') on a specific resource ('an instance previously placed on your account'), and scopes it to vast or runpod. This separates it from sibling tools like rental_status or rent_best.

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?

The phrase 'previously placed on your account' establishes the precondition and target context. It does not explicitly name alternatives or exclusions, so an agent must infer that other rental-related tools are for status or creation.

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