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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds meaningful behavioral context beyond them: it is 'fail-closed,' blocks SQL write tools, and 'Returns compliance_loop + buy URLs.' This helps an agent understand the tool's safety posture and outcome without contradicting the annotations.

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 four short sentences, each providing essential information: type, blocking behavior, exclusions, and return value. It is front-loaded with 'fail-closed policy' and avoids fluff. Some phrasing like 'Session/Cert OFF TABLE as primary' is cryptic but concise, so it loses a point for clarity while remaining efficient.

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 zero-parameter policy tool, the description covers the core purpose, the exact gating condition, and the expected return values. An output schema exists, so return details need not be fully restated. Minor gaps like what 'PASS + verify' entails procedurally keep it from being perfect, but it is sufficiently complete for an agent to invoke it 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?

The input schema is empty with zero parameters, so the baseline is 4. The description does not need to explain parameter semantics, and the schema coverage is 100%. No additional parameter information is necessary.

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 is an 'Embeddable ABMP fail-closed policy' and specifies its action: 'Agent runtimes MUST block SQL write tools until Pilot Challenge Exact $100 unlock (or Gateway invoice $299) PASS + verify.' This is a specific verb+resource+condition that distinguishes it from sibling tools like sqlguard_affiliate or sqlguard_balance, which have different purposes.

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 explains when to use this tool: before SQL write tools are allowed, until a payment/verification condition passes. It also provides a when-not: 'Session/Cert OFF TABLE as primary,' which excludes alternative payment/certification paths. This gives clear context for choosing this policy over siblings.

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