Cite Dataset Provenance

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

Annotations already mark the operation read-only, idempotent, and non-destructive. The description adds meaningful behavioral context by stating the result is not a freshness guarantee, does not itself verify currency, and that the returned provenance may be cited, which tells the agent how to treat the output and its limitations.

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 trigger use-case is front-loaded, followed by a compact list of returned fields, then the citation-binding guidance and an explicit caveat. The pre-trust workflow sentence earns its place as routing context; no sentence is wasted or redundant.

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 read-only provenance tool with a rich output schema and fully documented parameters, the description covers trigger, scope, return contents, limitations, and the intended surrounding workflow. There is no meaningful missing context that an agent would need to select or invoke it correctly.

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?

The schema fully documents dataset_ids with type, min/max, canonical examples, and a note that it is not a live freshness check (100% coverage). The description reinforces dataset identity and citation binding but does not add new parameter-level meaning beyond the schema, so the baseline of 3 is appropriate.

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 opens with a concrete trigger ('can I cite this source?') and states the resource: citation-ready dataset provenance. It enumerates the returned contents (source, steward, licence/attribution, canonical URL, evidence context), making the tool's scope unambiguous and distinguishing it from the sibling verify/evidence tools that serve a different stage.

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?

It explicitly names when to use the tool ('Use when asked can I cite this source?, for licence and attribution, or for citation-ready provenance'). It also gives a pre-trust workflow (search_datasets -> verify_dataset -> get_provenance) and warns that this is not a freshness check, though it does not name alternative tools for freshness or licence search such as get_freshness_summary or find_by_licence.

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