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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious operational context: no key is required because Pipeworx fronts one, and a personal free DPLA key can be passed as _apiKey. It doesn't cover failure modes such as an unknown id, which keeps it from a 5.

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?

Front-loaded with the core purpose, with the field list and auth note following. The field enumeration is a long run-on but each item is informative for an agent that must decide whether this tool returns what it needs; minor trimming would help.

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 does the work of describing return fields, which is exactly right for a detail-fetch tool. Combined with auth handling and the id-source reference, an agent has enough to call it correctly; only error/not-found behavior is unaddressed.

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% — both `id` (with its hex-format note and provenance from dpla_search_items) and `_apiKey` (with the self-service signup URL) are already documented in the schema. The description largely restates that, adding only the inline example call, so baseline 3 is correct.

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+resource+scope: 'One DPLA record in full by its id,' then enumerates exactly which fields come back. That enumeration makes it trivially distinguishable from dpla_search_items (which finds ids) and dpla_collections.

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 establishes the retrieve-by-id role and points to dpla_search_items as the source of the id, plus a concrete example call. It doesn't state explicit exclusions (e.g. 'do not use to search by keyword'), but the search-vs-fetch split is obvious from context.

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