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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two genuinely non-structured facts: claims carry evidence ids, and include_evidence returns 'the full evidence records as well (large)' — a response-size warning. That is useful but thin; nothing is said about unknown-asset behavior, lookup semantics, or cost, so a 3 is appropriate.

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, and the resource identity is front-loaded ahead of the optional-parameter caveat. The long comma-separated field list is dense but each item conveys real content about the payload. Minor cost: the list is slightly encyclopedic for a tool description.

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 carries the burden of describing the return shape, and it does so by enumerating the record's sections and explaining the evidence-id linkage. The read-only/idempotent annotations cover the behavioral side. Missing only error/not-found behavior and any notion of record size for the default (non-evidence) payload.

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 100%, so both parameters are already documented in the schema (asset id formats, include_evidence default false). The description reinforces include_evidence by flagging the payload as large and explaining that claims reference evidence ids, but adds no new format or constraint detail. Baseline 3 fits when the schema carries the load.

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 exactly what the record contains (identity, tokenization, provenance, components, hashes, rights, facts, unknowns, counts), which tells an agent this is the comprehensive asset lookup rather than a narrow one. It never states the verb 'retrieve/fetch' and never explicitly differentiates itself from siblings like ruthven_get_provenance or ruthven_get_evidence, so it falls short of a 5.

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 use this tool versus ruthven_get_provenance, ruthven_get_evidence, or ruthven_describe. The only guidance-like content is the note that include_evidence=true is 'large', which is a parameter tradeoff, not tool-selection guidance. An agent must infer when the universal record is preferable to the narrower sibling lookups.

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