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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is fully covered by structured data. The description adds that the record supports offline verification via manifest and verifier links, which is useful behavioral context, but it says nothing about error handling for a missing/invalid id or the cost of a lookup.

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?

Two sentences with no filler: the record contents are front-loaded, then the invocation rule. The first sentence is dense with an aside ('the top one in full without a licence') but every element maps to a real field, so it earns its length.

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 usefully stands in by describing the return payload (subject, grade, findings, capabilities, evidence roots, manifest, verifier links). For a two-param, annotation-covered read tool this is nearly sufficient; only error/fallback behavior for unresolved ids is missing.

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 carries the full burden, and it does substantial work: it enumerates the accepted id forms (report, d1:, f1:, manifest sha256) and explains that domain returns the latest record. It stops short of clarifying the 'latest' semantics or precedence when both parameters are given, so it is strong but not complete.

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 enumerates the concrete contents of the record (subject, grade, findings, capabilities, evidence roots, manifest, verifier links) for 'one observation', which makes the resource specific rather than tautological. The verb is implicit — it reads as a noun phrase listing contents rather than an explicit 'retrieve' action — but the resource is clear enough that no sibling (explain_finding, registry_lookup) is easily confused with it.

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?

'Give id ... or domain for the latest' tells the agent the two entry paths and the id formats, which is real invocation guidance. However there is no when-to-use vs when-not guidance, no indication of which sibling to prefer, and no hint of what happens if both id and domain are supplied. Usage is implied rather than scoped.

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