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

The description adds valuable behavioral details beyond annotations: it is deterministic, uses no LLM, and costs 1 credit. It also states the return type (allow/deny with reason). The annotation idempotentHint and destructiveHint are consistent, and no contradiction exists.

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 concise—four sentences, each adding information: purpose, return value, prerequisite, and behavioral traits. It is front-loaded with the core function and avoids fluff.

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 output schema exists and annotations are present, the description covers necessary context: what the tool does, what it requires, and its cost/determinism. It is complete enough for an agent to decide whether and how to invoke it.

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 description coverage is 100% with detailed descriptions and an example for proposed_action, so the description need not repeat parameter semantics. The only param-related addition is the prerequisite mention, which applies to the overall call rather than to a specific parameter.

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 evaluates a proposed agent action against governance policies, using a specific verb ('Evaluate') and resource ('your governance policies'). It distinguishes itself from siblings by focusing on policy-based allow/deny, unlike dedupq_check or qualitygate_validate.

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 provides an essential prerequisite: at least one active policy created via guardrail_create_policy, which tells the agent when the tool is usable. It does not explicitly name alternatives or exclusion cases, but the context implies this is the policy-checking tool.

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