curation_review

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

Beyond the annotations (readOnly=false, idempotent=false, destructive=false) it discloses real behavior: outputs are limited to suspect-or-worse spots, capped by max_rows (default 100) with total-vs-shown counts in named fields, unknown file_ids raise an error, and EIC series/spectra are deliberately not returned. It also explains that the HTML viewer performs the Submit and writes _tags.xml. The only gap is that it never says what files/artifacts are written on disk by this call itself (e.g., the HTML path's lifecycle).

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?

Bold section markers (prerequisite, target/scope, return values, judgment taxonomy) make it well front-loaded and skimmable. It is long, and the exhaustive enumeration of likely_wrong/suspect codes (polarity_mismatch, precursor_unmatched, dmz_out, class_rule_rejected, adduct_isomer_of, etc.) is denser than strictly needed to invoke the tool, but each item is substantive rather than filler.

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?

There is no output schema, so the description carries the return contract—and it does: TSV of suspect+ spots, ordering, named count fields (n_table_rows_total, n_table_rows_shown), per-class trend summary contents (scores, R², outlier counts), and the html_path. Combined with the workflow hand-off to curation_flags and curation_submit, an agent has everything needed to call it and interpret the result.

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%, so the prose must carry all semantics; it explains file_ids (only IDs present as .arf rows, else error), max_rows (default 100, heavy-first ordering), ontology ("PG" class filter), name_contains (partial name match), and thresholds (with concrete defaults ppm_pass=5, ppm_borderline=10, drt_pass=0.5). However file_path and max_traces are never mentioned, leaving two of seven parameters undocumented anywhere.

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 sentence names a specific action and artifact: it builds a review table of annotated spots containing EIC, mirror plot, Δppm, ΔRT, RT–m/z trend and machine discrimination. It also clearly separates this from curation_suggest/curation_submit/curation_flags by describing the review-and-submit workflow, so an agent can identify the tool without opening the 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?

It states the prerequisite explicitly ('先に library_load', recommending the *_Loaded.msp2.dbs), explains the default scope versus the ontology/name_contains filters, and gives the exact fallback condition for hitting curation_submit (pasted Copy text / submit.via == "copy"). It also says where to verify submitted results (curation_flags), so the when/how of use is fully prescribed.

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