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

With no annotations, the description carries the full behavioral burden and meets it: it discloses a $0.01 USDC charge, the external third-party seller, the Base settlement, the blocking/refund behavior for over-limit commands, and that it returns a verdict rather than executing the command. This goes well beyond what the schema or annotations provide.

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?

The description front-loads the most important facts: cost, optionality, and purpose. Each sentence adds distinct value—purpose, return value, usage context, cost/refund behavior, and relationship to internal checks—without redundancy or filler.

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?

Given a single parameter, an output schema, and no annotations, the description covers the key operational context: cost, external party, refund policy, verdict contents, and the fact that this is an optional supplement to internal safeguards. No critical information an agent needs to invoke it correctly 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 coverage is 0%, so the description must compensate. It does clarify that 'command' means a proposed command or tool call to be preflighted, and ties it to 'external tool calls.' It could have given a concrete format example, but with a single string parameter and repeated context, an agent can infer the intended value.

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?

The description opens with a specific verb ('Preflight') and resource ('HumanMirror Safe Preflight'), and clearly states what is returned: an independent risk verdict with risk level, findings, and required guards. The optional third-party angle differentiates it from sibling tools like sandbox_simulate and the internal check tools.

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 tells the agent when to use it: 'for genuinely risky external tool calls where a second opinion matters.' It also clarifies that this is optional, that AgentWorld's own layers remain primary and free, and explains the paid/refund behavior. This is strong when-to-use and when-not-to-prioritize guidance.

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