export_bibliography

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered. The description adds little behavioral context beyond the transform nature of the tool; it says nothing about determinism of output formatting or handling of malformed paper objects.

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?

One sentence, front-loaded with the action and followed by the accepted output formats. No wasted words.

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 values need no explanation, and the tool is a simple deterministic transform. The description is nearly complete, only omitting the bibtex default and any hint about the expected paper object shape.

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 description coverage is 0%, so the description must carry the load, and it does: it enumerates the three valid format values (bibtex, ris, csl-json), which the schema does not provide as an enum, and explains where the papers array comes from. It does not mention the default of bibtex, but the key semantics are supplied.

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 (format/export) and resource (papers) plus the concrete output formats, so the agent knows exactly what this produces. It does not explicitly contrast itself with siblings like verify_citation, but the transform-vs-retrieve distinction is obvious from the phrasing.

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?

"as returned by the search tools" implies the input should come from prior search results, which is useful context. However, there is no explicit when-to-use or when-not-to-use guidance, and no named alternative for citation-related tasks.

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