library_plot_mirror

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

With readOnlyHint already covering safety, the description adds substantial non-obvious behavior: unscored peaks below the `.dbs` intensity cutoff are drawn faint gray rather than dropped, that layer is excluded from label slotting, and legend/caption counts appear only when such peaks exist. It also documents the greedy descending-intensity collision scan and that the payload format is `lipidmix.mirror.v2` with an added `unscored_mz` layer.

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?

Front-loaded and bolded where it matters, but over-long for a four-parameter tool: the upstream MS-DIAL digressions (CreateAxisPropertySelectors2 selectors, the `Overlap="Horizontal, Direct"` OR-degeneracy argument) are rationale that does not change how the agent calls the tool. The behavior it explains is still correct, so it is verbose rather than wasteful.

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, so the description supplies the return contract itself (server-rendered PNG vs. rounded-coordinate `lipidmix.mirror.v2` JSON), and it discloses the `ms2_tol` inheritance from stored `search_params`. Everything needed to call it correctly and interpret the result is present.

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 carries the full burden and does: it gives the value set and default for `scale` (relative/sqrt/log10) and explains why `Absolute` is deliberately omitted, defines `label_policy` semantics ('auto' 2-D vs 'msdial' horizontal-only), and clarifies `rank` as selecting among ranked candidate references. This is meaning well beyond bare `type: integer/string`.

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 ('対向プロット（mirror plot）を描く') plus the exact data source ('直近の library_match_feature 結果'), so an agent knows both the action and its input. No sibling in the list produces mirror plots, so there is no ambiguity to resolve.

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 frames the two output modes: default PNG rendering on the server vs. `output="payload"` for clients that draw themselves (naming Use-LLM as the case). It also gives a concrete trigger for `scale="sqrt"` ('precursor がベースピークのスペクトル'). Missing only an explicit statement of when not to call it (e.g. no prior match result exists).

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