Checks a single peak annotation for mass error ppm and adduct/ion-mode consistency, returning a dossier with knowledge links to assess biochemical validity.
指定した1ピークのアノテーションが生化学的に妥当かを検証するドシエを返す。
分析化学的な同定確度（精密質量誤差ppm・アダクト/イオンモード整合）を決定的に 判定し、生物学的妥当性は関連 knowledge slug を添えて LLM の判断に委ねる。 先に pai2_parser でデータを読み込むこと。peak_id か peak_name の いずれかを指定する。
| Name | Required | Description | Default |
|---|---|---|---|
| peak_id | No | ||
| peak_name | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the safety profile is covered, yet the description still adds real behavioral context: which judgments are deterministic versus which are deferred to the LLM with supporting knowledge slugs. That division of labor is the key thing an agent needs to interpret the result and is not derivable from the annotation. No mention of cost, latency, or behavior when neither parameter is given.
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?
Four short lines with zero filler: purpose first, the analytical/biological split second, the prerequisite third, and the parameter constraint last. Every sentence contributes information an agent would otherwise have to guess.
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?
With no output schema, the description is responsible for conveying the return shape, and it does so at a conceptual level (a dossier containing a deterministic verdict plus knowledge slugs). The internal structure of the dossier and the failure mode when neither identifier is supplied remain unstated, which is a modest gap for a read-only inspection tool.
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% and both parameters are nullable with no required field, so the description carries the burden. It does so by stating that exactly one of peak_id or peak_name must be specified, a mutual-exclusivity rule the flat anyOf schema does not express. It does not explain format (ID syntax) or the precedence behavior if both are passed.
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 names a specific verb and resource: it validates the biochemical plausibility of a single peak's annotation and returns a dossier. It further splits the deliverable into a deterministic analytical-chemistry verdict (ppm error, adduct/ion-mode consistency) and a biological verdict delegated to the LLM, which tells an agent exactly what kind of answer to expect. It does not contrast itself with any sibling besides naming the prerequisite loader.
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 states a clear prerequisite ("run pai2_parser first to load the data") and imposes an invocation constraint that peak_id or peak_name must be supplied. There is no explicit when-not guidance or comparison against adjacent tools such as pai2_inspect_peak or library_match_feature, so it stops short of full alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.