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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. On top of that the description adds genuinely useful behavior the annotations cannot convey: the confidence rubric per entity type and the guarantee that it "Never repeats evidence text", which tells the agent what the response will and will not contain. Missing is what happens for invalid or stale refs.

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?

Purpose and scope are front-loaded in the first sentence, and the bulk of the text is a tightly structured, parallel rubric covering all seven entity types. The rubric is dense but every clause defines a distinct confidence tier, so it earns its space; a reader still has to parse a long single block to find the rule for one type.

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 a trivial one-parameter input, a declared output schema, and full annotation coverage, the description supplies everything needed to call it correctly plus the interpretation guide for the returned confidence levels. The only omission is edge-case behavior for unknown or expired refs, which is minor for a read-only lookup.

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 0% and the lone `refs` property has no description in the schema, so the description must carry the load — and it does: it explains that refs are opaque identifiers obtained from other Dactic tools and that 1-20 are accepted. That is materially more than the bare array-of-strings schema conveys; only the per-item string format remains unspecified.

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?

"Describes each item's source and a confidence of high, medium or low ... with the rule that applied in `basis`" is a specific verb-plus-resource statement, and the phrase "For refs returned by other Dactic tools" positions it as a follow-up/provenance step rather than a primary retrieval tool like get_entity_context or fetch. It stops short of naming an actual sibling, so the differentiation is implied rather than explicit.

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 description gives a clear trigger condition: call this when you hold refs produced by other Dactic tools, and it caps the batch at 1-20. It does not state when NOT to use it (e.g., when a ref is unknown or when freshness, not provenance, is the question) or point to alternatives for that case, which keeps it below a 5.

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