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

No annotations are provided, so the description carries the full disclosure burden. It does add genuinely useful non-schema behavior: per-query cost ($0.001), a free first verdict per operator, and inclusion on Fleet/Fleet Pro plans. However, it omits read-only vs mutating nature, auth requirements, rate limits, and whether verdicts are cached or recomputed, which leaves real gaps for a zero-annotation tool.

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?

Compact and front-loaded: the verdict semantics lead, with pricing supplementary. Every clause carries information, though the pricing sentence is dense and slightly tangential to the tool's function.

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 and no annotations, the description partially compensates by enumerating the verdict values (OK/DIVERGENT/STALE/CROSS_TENANT_RISK/UNSEEN), which is the most important return-value information. It falls short on the meaning of the sole parameter (server vs. partition), auth/cost prerequisites, and any notion of when the verdict is stale.

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% and the single required parameter 'server' is undocumented in both schema and description. The description says 'per-partition' but never explains how the server argument maps to partitions or what format the server identifier takes, so it fails to compensate for the coverage gap.

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 names the resource precisely ('per-partition cache-exposure verdict') and enumerates the exact verdict values it can return, so an agent knows the output domain. The verb is implicit (it never says 'computes/returns'), and it does not differentiate itself from guard_diff_check or guard_tools_list, but the noun-plus-enum phrasing is specific enough to distinguish the tool's role.

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?

There is no statement of when to reach for this tool versus the sibling guard tools, and no prerequisites or preconditions are given. Pricing tiers are mentioned but that is billing context, not usage guidance.

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