export_research_tool

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

With no annotations provided, the description carries the full burden and does so well. It explicitly discloses that the tool returns raw LaTeX rather than a rendered PDF, explains the calling agent's responsibility to save and optionally compile the file, and states the exact return type. This is behaviorally transparent beyond what the schema provides.

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 description is front-loaded with the key distinction that it returns LaTeX rather than a PDF, then uses numbered steps and an Args/Returns structure that is easy to scan. It is somewhat long and repeats the instruction to always save the .tex file, but the repetition reinforces an important workflow requirement rather than adding noise.

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?

Given the tool's multi-step workflow, four parameters, lack of annotations, and presence of an output schema, the description is complete enough for an agent to call it correctly. It covers purpose, non-rendering behavior, parameter semantics, return value, and post-call handling instructions. Nothing essential 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 description coverage is 0%, so the description must compensate, and it does: every parameter is documented with meaning and expected format. It explains that conversation_summary is plain text, literature_recommended is a list of bullet lines, liked_articles contains citation dictionaries with title/authors/year/link keys, and citation_formats is a subset of APA, Chicago, and MLA.

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 clearly states the specific action and resource: it builds LaTeX source for a research export containing a literature review, conversation summary, and citations. It also sharply distinguishes what the tool does not do by stating it does not render a PDF. It does not explicitly contrast itself with the sibling search tools, so it falls short of a 5.

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 implies the tool is for producing a research export, and it gives detailed post-call handling instructions for the returned LaTeX. However, it does not state when an agent should choose this tool over alternatives or specify exclusions beyond the PDF-rendering clarification. Usage guidance is therefore adequate but incomplete.

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