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

Annotations only declare readOnlyHint=true, and the description goes well beyond that: it discloses conditional return fields (version_count, source_count, first_edition_seen, last_edition_seen appear only for multi-form/multi-source records), per-row source attribution, and that records from older editions are flagged. This is meaningful behavioral context, though phrased opaquely.

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?

The description is a wall of long, comma-spliced sentences with the core purpose buried after tangents about version counts and edition stamps. Key information is not front-loaded, and several sentences restate the same conditional-field idea in prose and field names.

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 thoroughly — enumerating returned sections, conditional fields, and per-row provenance. It is dense but covers the complexity of a rich single-record fetch adequately.

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 100% and the single parameter's origin ('from learning_units or get_checklist') is documented in the schema, so the description owes little here. It adds no format or syntax detail beyond the schema, so the baseline of 3 applies.

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 states a specific resource and enumerates its parts (row, prerequisites, aliases, terms, articulation statements, transfer frameworks), so an agent knows this retrieves one fully-assembled learning unit. It implicitly distinguishes itself from list tools ('come from the one-record get, never from a list') but never names a sibling tool 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?

There is implicit routing guidance ('The forms themselves ... come from the one-record get, never from a list'), which hints at the list-vs-get distinction. However, it never states when an agent should call this versus learning_units, get_checklist, or compare tools, so usage is only inferable.

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