guard_action

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

With no annotations, the description fully discloses behavioral traits: it is paid (~$0.02 per call, x402/USDC), fail-closed (uncertainty escalates to review, red flags block), returns a decision/risk/reasons/safer_alternative, and explicitly states pricing is disclosed and Verity holds no key. It also clarifies that affiliate_id never changes price or behavior. This goes well beyond basic operation and gives the agent a complete picture.

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 is lengthy (~170 words) but well-structured with paragraphs: purpose, pricing, fail-closed behavior, return values, and affiliates. It front-loads the core purpose and adds essential behavioral details. Some phrasing is somewhat promotional ('THE MONEY-LINE GATE', 'honest 0-1 risk'), but it earns its length by covering key operational facts.

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 tool with no output schema, the description thoroughly explains the return structure (decision, risk, reasons, concerns, safer_alternative) and the fail-closed behavior. It also covers pricing and audit artifact. The main gap is parameter documentation for policy/context, but the tool's purpose and behavior are otherwise well-specified, making it usable for an agent in the intended high-stakes scenario.

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 schema has 0% description coverage, so the description must compensate. It explains affiliate_id (optional referral tag, no behavior change) and references 'action' implicitly, but provides no meaning for 'policy' or 'context' parameters. The agent is left to infer how to structure these fields, which is a significant gap for a 4-parameter tool.

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 clearly states the tool decides whether a proposed agent action should proceed, specifically before irreversible actions like payments, messages, destructive commands, or data sharing. It distinguishes itself from siblings by framing itself as the 'money-line gate' for irreversible commitments, versus the verification/security tools in the sibling list.

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?

It explicitly says 'use this right before the agent SPENDS, SENDS, or commits something irreversible,' providing precise trigger conditions. It also contrasts itself with 'free local checks,' implying that for reversible or low-risk actions a local check may suffice, though it does not name specific sibling tools or provide explicit exclusions.

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