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

Annotations describe a safe read-only, idempotent, closed-world tool. The description adds real behavioral detail beyond that: it is free, makes no network call, never resolves or invents a value, drops non-dchub URLs into `omitted`, and substitutes RETRIEVED when as_of is missing. The licence-per-layer disclosure explains what the caller may legally do with the output, which annotations cannot express.

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-loads the trigger ('Use right before you QUOTE...') and keeps the when-not warning last, which is good ordering. It is however long and dense, with capitalized emphasis and a licence digression that consumes several lines; useful, but more verbose than strictly needed.

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?

For a zero-required-param, output-schema-backed tool with a surprising licence model, it covers the edge cases an agent must anticipate: missing as_of, invalid url, missing layer, and the over-claim risk of flattening a composite layer to CC-BY-4.0. The enumerated return fields are redundant given the output schema but harmless.

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%, so the baseline is 3, but the description adds value beyond the schema: it explains that `layer` determines the licence line and that omitting it yields a scoped statement rather than a grant, and that a non-dchub `url` is dropped and named in `omitted`. It also frames the params as 'what you read off the response you are citing'.

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 and deliverable (returns one paste-ready attribution line for a value about to be cited) and names its exact scope. It explicitly distinguishes itself from the data tools ('Do NOT use to look a figure UP; call the data tool first'), so an agent can route correctly without opening the schema.

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?

Gives both the trigger ('right before you QUOTE a DC Hub figure to a human') and the exclusion ('Do NOT use to look a figure UP'), plus the precondition that a figure must already have been read. Nothing is left to inference.

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