datasheet_fetch

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses the cache location and naming scheme, the JSON sidecar contents, the cache-hit behavior, re-fetch on hash mismatch, and the exact refusal conditions (non-http(s) URL, >50 MB, >60 s timeout, missing %PDF header) with nothing stored. It also notes the page-count limitation for compressed files.

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 purpose, then reading instructions, cache behavior, refusal rules, args, and returns. It is long but most sentences earn their place. The Returns section partially restates an existing output schema and could be trimmed.

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 a fetch tool with no annotations, two parameters, and an output schema, the description covers everything an agent needs: what it produces, where the file lands, caching semantics, failure modes, and sidecar metadata. The output schema handles return shape, and the description adds only useful caveats like pages possibly being None.

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 does: url is described as the http or https URL, ideally the manufacturer's own, and part_number is explained as recorded in the sidecar for the citation. Both parameters gain meaning beyond their bare titles.

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 first sentence gives a precise verb and resource: it downloads a datasheet PDF into the workspace and returns its path. The description also explicitly states the non-goal ('nothing here parses the PDF'). It does not name a sibling such as part_fetch or lib_audit_footprint_vs_datasheet, so sibling differentiation is implicit rather than explicit.

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 tells the agent to use the returned path itself and read the package drawing and land pattern pages, and it gives a clear fallback for refused cases: download in a browser and read the local copy. It does not compare against alternative tools like part_fetch or lib_dblib_search, leaving the agent to infer when this tool is preferable.

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