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

Annotations already declare readOnly/idempotent/non-destructive, so the description goes beyond them productively: pagination of inline entries vs. a downloadUrl that always contains the whole selection, default recordType=editions also emitting work-level citations, stable unique citation keys, and escaped fields. Missing only things like any size or rate limits on the export.

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?

Front-loaded with the core capability and download artifact, then progressively adds filter behavior and edge cases. Sentences mostly earn their place, though the sentence about citation keys and escaped fields is fairly dense.

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, and the description compensates by describing the return shape (BibTeX text plus downloadUrl) and its pagination semantics. For a read-only export tool with strong annotations, this is nearly complete; the only real gap is the breadth of filter parameters.

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% for a 5-parameter schema with a nested object holding roughly 28 sub-filters, so the description carries the full burden. It names a handful of dimensions (workIds, publicationIds, Basel references, author, language, year) and clarifies recordType's default, but leaves many filters such as full, labelIds, topicIds, workTypes, journalScope, downloadFormats, originalYearFrom/To and pageSize/offset unaddressed.

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 ('Generate standard UTF-8 BibTeX and a direct .bib download URL') with the scope of records ('all matching works/editions/translations'). This is clearly distinguishable from siblings like get_publications, list_works or get_bibliography_source without opening any schema.

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?

Explicitly explains the empty-filter case (whole bibliography) versus filtered exports, and enumerates the filter dimensions that select subsets. It also adds a conversational guideline ('tell the user BibTeX is available and ask whether they want it'). No sibling tool is named as an alternative, so it misses the top tier.

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