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

Annotations already mark the call as read-only and non-destructive; the description adds real behavioral detail by capping input size at 25 and disclosing per-item error behavior for missing publication metadata. This is more than redundant with the structured annotations.

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 dense sentences deliver scope, options, constraints, and target-selection guidance with no filler. Every clause contributes new functional information, and the most important disambiguation ('choose page…') is placed at the end as a decision rule.

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 export tool with an output schema already available, the description covers the essential invocation decisions, edge-case behavior, and target-selection logic. There is no obvious missing piece an agent would need to successfully call it.

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?

With 0% schema description coverage, the description carries the full parameter burden, and it covers all three parameters: IDs (1–25 VHP IDs or URLs), format (text or ris), and target (publication or page, with page's purpose clarified). This provides enough semantic information for an agent to construct correct calls.

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 action ('export citations') with a clear resource scope (1–25 VHP IDs or URLs) and defines the two dimensions that shape the output (format and target). This is unmistakably distinct from read/search/collection siblings and leaves no doubt about what the tool produces.

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 gives actionable context for choosing the 'page' target ('choose page to cite a biography or history page') and warns about the failure mode when publication metadata is missing. It does not explicitly name sibling alternatives, but none of the listed siblings are citation-export competitors, so the contextual guidance is sufficient.

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