pai2_parser

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

readOnlyHint=true already establishes the safety profile, and the description adds substantive behavior beyond it: the exact summary payload returned, the constraint that PAI2 is a single-sample unit, and the implicit requirement that a same-named .dcl exist for MS/MS (with dcl_index matching list order). It does not mention failure modes for missing/malformed files or the effect of filter_threshold, which keeps it from a 5.

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 purpose and return contents are front-loaded in the first two sentences, followed by scope exclusions and follow-up routing. Every sentence carries information, though the .dcl sidecar note is slightly buried at the end rather than flagged as a precondition.

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 well by enumerating the returned distributions and top-peak ranking, plus the single-sample limitation and sidecar dependency. The remaining gap is parameter-level guidance for filter_threshold, which is not covered anywhere else in the structured data.

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 both parameters, so the description carries the full burden — but it never mentions file_path or filter_threshold. The optional numeric filter_threshold in particular has no stated semantics (units, whether it applies to intensity or S/N, default behavior when null), leaving an agent to guess its meaning.

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 ('1つの .pai2 を解析し、ピーク在庫の要約を返します') and immediately enumerates what the summary contains (annotation status, m/z, RT, intensity, S/N distributions, top-intensity ranking). It also differentiates itself from arf_parser/arf2_parser and from pai2_inspect_peak, so an agent can place it in the family without opening schemas.

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 states a when-not condition — PAI2 is single-sample so cross-sample/multivariate comparison (omics PCA) is out of scope — and names the alternatives (ARF/ARF2) for that case. It further routes follow-up work to pai2_inspect_peak / verify_peak_annotation and MS/MS to the .dcl sidecar, covering both escalation and data dependencies.

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