guard_action

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

The description details behavioral traits beyond what annotations would provide: fail-closed behavior ('will not allow what it cannot justify as safe'), return values (decision, risk score, reasons, concerns, safer alternative), and mentions it produces an independent, signed verdict and maps to OWASP. No annotations are present, so the description bears full responsibility and meets it well.

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 verbose (about 10 lines) and includes dramatic phrasing like 'THE MONEY-LINE GATE' and 'the thing no free local check can give.' While it is front-loaded with purpose, it contains extraneous details that could be condensed. It earns its place but could be more concise.

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 the tool's complexity and lack of annotations or output schema, the description covers main behavioral aspects (fail-closed, return structure) and maps to OWASP. However, it omits explanations for the 'policy' and 'context' parameters and does not mention prerequisites or permissions. It is moderately complete but has notable gaps.

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 input schema has three parameters (action, policy, context) with 0% description coverage. The description only meaningfully explains the 'action' parameter by referring to 'proposed agent ACTION,' but does not explain 'policy' or 'context.' Given low schema coverage (<50%), the description should compensate but fails to add clarity for two of three parameters.

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's purpose: to decide whether a proposed agent action should proceed, specifically before irreversible actions like spending, sending, or destructive commands. It distinguishes itself from siblings (detect_injection, moderate_content, redact_pii, verify_fact) by focusing on guarding irreversible actions, making its purpose distinct and well-defined.

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 description explicitly advises when to use the tool: 'right before the agent SPENDS, SENDS, or commits something irreversible.' While it does not explicitly state when not to use it or list alternatives, the context implies it is specifically for high-stakes actions. The guidance is clear but lacks explicit exclusion criteria.

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