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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description goes beyond that by defining the meaning of the verdict ('compliant:true only means the delegation chain is shallow and KL is under epsilon'), which is the single most important behavioral fact and is not in the annotations. It does not mention threshold values or what a failing response contains beyond the schema's hint about quarantine_escalation.

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?

Three tight sentences with the core mechanism front-loaded and the caveat immediately after; nothing is padded. Minor deductions for unexplained internal jargon ('GOV-100', 'epsilon') that costs the agent a beat without adding routing value.

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?

With no output schema, the description carries the burden of explaining the return value, and it does so by pinning down the meaning of compliant:true and the escalation path. What remains unstated is the actual epsilon threshold and whether a failure returns a reason code, but the essential call-correctly information is present.

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%, and the schema already documents that `description` is ignored and that high chain_depth escalates to quarantine_escalation. The description only restates which two parameters are read, adding no format, range, or default detail beyond the schema, so the baseline 3 applies.

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?

States a specific mechanism: a delegation-depth plus KL-divergence gate (GOV-100), and names exactly what it reads (chain_depth, kl_divergence). The negative clause 'does NOT evaluate GDPR/CCPA' separates it from the many sibling compliance_* tools (compliance_eu_ai_act, compliance_fairness, compliance_transparency) without the agent needing to open schemas.

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 exclusions ('does NOT read your data description', 'does NOT evaluate GDPR/CCPA') implicitly route the agent away from this tool for regulatory-compliance questions, which is useful negative guidance. However, no sibling is named as the alternative and there is no explicit 'use this when...' trigger, so the routing is left to inference.

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