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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description reinforces this with 'stores nothing and makes no network requests' while adding genuinely new behavioral context: missing controls and incomplete observations are marked unresolved, and the output explicitly declines to claim causation, compliance, or a verified fix. That epistemic framing is not derivable from annotations or schema.

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 short sentences, front-loaded with what is compared, followed by resolution rules and then the explicit non-claims. No filler and nothing restated.

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 an output schema present and rich annotations, the description need only cover inputs and stance, which it largely does. It stops short of stating what happens if the two snapshots differ in domain or method, or how unresolved phases surface, but the core is covered.

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 0%, so the description must carry the load. It contributes the same-domain constraint and the phase-by-phase comparison model, but leaves baseline-vs-current ordering, the const method/observationWindowMs values, and the required phase triple unexplained beyond the structural schema.

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 verb and resource ('compares two supplied RegSentry runtime snapshots of the same domain, phase by phase'), including the important qualifier that the snapshots are supplied rather than fetched, which separates it from the inspection siblings. It never names an alternative tool outright, so an agent must infer that inspect_runtime_consent produces the inputs.

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 'two supplied ... of the same domain' phrasing implies the precondition (both inputs must be captured from the same domain) but does not say when to reach for this instead of interpret_consent_evidence or export_consent_report. Usage is inferable from the comparison framing rather than stated.

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