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

With zero annotations the description carries the full burden, and it does disclose real behavior: per-file nucleus/frequency extraction, per-row field_mhz and field_source reporting, explicit precedence (a file's stated frequency always wins over the field_mhz argument), and the no_data_found error status. It omits authentication requirements for api_key, any limits on archive size or concurrency, and whether partial failures still return results.

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?

Three short paragraphs, front-loaded with what the tool does and what it returns, followed by the precedence rule and the failure mode. No filler sentences, though the frequency-precedence point is restated across two sentences.

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?

Return shape is covered by the output schema, so the description correctly doesn't dwell on it while still naming the key aggregates. With a 5-parameter, 1-required tool at 0% schema coverage and no annotations, the missing semantics for nucleus, solvent and api_key leave the definition incomplete for correct invocation.

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 only partly does: it clarifies that the required `folder` argument is a zip/tar URL and fully specifies field_mhz as a fallback-only value. The nucleus, solvent and api_key parameters receive no semantics at all in either schema or description, leaving half the surface undocumented.

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: batch-analyze every NMR data file in an archive, with the accepted container types (zip/tar URL) and the returned aggregates named. It distinguishes itself from the single-spectrum covnmr_analyze only implicitly via 'batch' and 'archive', never naming the sibling or the contrast explicitly.

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?

'Give field_mhz only for files that declare no frequency' and the no_data_found error case give useful conditional guidance for one input. But there is no explicit statement of when to choose this over covnmr_analyze or covnmr_identify, nor any prerequisites (api_key, archive size/format limits).

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