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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description adds genuinely new behavior: it rechecks draft/source freshness, stale or unverified scores are excluded, and it contains no human approval. That is meaningful disclosure beyond 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?

Three tight sentences, front-loaded with the core purpose, then behavioral caveats, then output-reading guidance. Dense but every clause carries information; slightly telegraphic phrasing costs it the top score.

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 compensates by naming the fields to inspect (nextOffset, evaluated/total) and warning about freshness revalidation. The remaining gap is the undocumented nested revision fields, which an agent must still infer from the schema.

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 coverage is only 50% and the nested reportRevision object (outputJobId, payloadHash) has no field descriptions at all. The phrase 'exact report revision' hints at precision but adds no format or validation meaning beyond what the schema patterns already encode.

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 ('Read') and resource ('stored advisory evidence review') with a scoping qualifier ('by exact report revision'). This clearly separates it from write-oriented siblings like helvabase_review_draft_evidence or helvabase_add_evidence_version, though it never names an alternative directly.

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?

Implies the usage context ('by exact report revision') and gives one downstream instruction ('Read nextOffset and evaluated/total before describing coverage'), but never says when to choose this over sibling read tools or what prerequisites (e.g. a prior review) are needed.

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