export

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

With no annotations, the description must carry the full disclosure burden, and it does: automatic publication-date bisection, summary-only return with sha256, path must not already exist (no overwrite), a 100k record cap, possible database drift during retrieval, and an explicit warning that output is not byte-identical to PubMed's web export. It discloses shard-count verification against the total. This is unusually rich behavioral context for a write-to-disk tool.

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 core action is front-loaded, and every sentence carries information (format semantics, return shape, path constraint, cap, drift caveat). The semicolon-dense layout packs several distinct facts into single lines, which slightly hurts scannability but wastes nothing.

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?

For a complex, multi-mode, file-writing tool, this is nearly complete: format semantics, return-summary fields, path safety, caps, and caveats are all covered, and an output schema exists so return values need no further explanation. The only gap is as_json, which is never mentioned.

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 0%, so the description must compensate, and it largely does: all three format enum values are explained semantically (pure PMID list vs. core bibliographic fields without abstracts vs. .nbib with abstracts and MeSH), and the path parameter's no-overwrite constraint is stated. The as_json parameter is left unexplained, which keeps it below a 5.

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 opening clause states a specific verb and resource: fetch all PMIDs for a query and write them to a file. It also distinguishes itself from tools that return records by declaring it returns only a summary, so the agent can tell it apart from fetch_abstracts or search 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?

Usage context is clear: bulk export to disk with automatic bisection past the 9999 window, and a 100k safety cap. It does not explicitly name alternatives such as count or fetch_abstracts or when NOT to use it, so it falls short of the top band, but the context is unambiguous.

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