Format a reference list

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

With annotations only covering readOnly/openWorld, the description carries the real behavioral burden and does it well: it discloses sort order (alphabetical, except IEEE preserving input order because entries are numbered), graceful degradation for unknown references (appended as not found rather than failing the call), and omission of missing fields instead of fabrication, plus a caution to verify output.

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?

Dense but front-loaded: the batch behavior, sorting, and failure mode come before the input recap, and every clause carries information. The trailing example prompt and restated input formats are slightly redundant with the schema, keeping it from a 5.

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?

No output schema exists, so the description must explain the return value – and it does: an ordered reference list with not-found entries appended. Given a two-parameter, non-nested tool, nothing an agent needs to invoke 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 100% (both parameters fully described with the enum and the 1–10 item bounds), so the baseline is 3. The description restates the accepted identifier formats and style list without adding new syntax beyond the schema, so it neither compensates for a gap nor adds materially.

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 resource with scope ('turns up to 10 papers into a reference list in one call') and explicitly distinguishes itself from both format_citation (single) and get_papers (lookup only). An agent can tell exactly what this produces versus its 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?

Positions itself as the batch counterpart to format_citation and shares the get_papers lookup, which gives clear context for when to pick it. A worked example prompt reinforces usage, but it never states an explicit exclusion rule such as 'use format_citation for a single paper' – the routing is inferred from the batch framing.

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