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

Annotations already establish read-only, idempotent, open-world, non-destructive behavior, so the bar is lower. The description adds real value beyond that: entries come back as separate rows rather than a finished file, entries must be joined with a blank line, and unmatched inputs surface in an 'unresolved' collection — none of which the annotations convey.

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?

Three sentences, front-loaded with the capability, then the gotcha about row joining, then the failure mode. Every sentence carries information an agent needs; nothing is redundant with the title or schema.

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?

An output schema exists, so return-value structure need not be restated, and the description still flags the 'unresolved' field an agent should check. For a two-parameter, no-nesting formatting tool with full annotations, nothing needed to call it correctly is missing.

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 50% (only 'ids' is documented in the schema), so the description must carry the load for 'format'. It does: it names both output formats, enumerates the four accepted identifier kinds, and restates the 1–100 bound, adding meaning beyond the schema's minItems/maxItems constraints.

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 artifact (build BibTeX or RIS citations) plus the accepted identifier types and the 100-item ceiling, which is far more precise than the title alone. It does not name or contrast any sibling tool, so an agent must infer that this is the only export/formatter tool among fetch/query siblings.

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?

Usage is implied rather than stated: the description reveals this returns rows rather than a file, which tells an agent it must assemble the output itself, and that is useful context. There is no explicit when-to-use routing, no statement of when a sibling like get_papers would be better, and no note on prerequisites such as resolve failure handling.

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