library_match_feature

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

With only readOnlyHint available, the description carries the full burden and does far more than required: it enumerates the exact status codes (`dcl_precursor_mismatch`, `spot_not_found`, `not_found`) and their triggers, documents default tolerance values, discloses that tolerance arguments affect only library candidate search and not the fixed internal `.dcl` spectrum window, and warns that ranking is an approximation of upstream ordering with known false-positive risk.

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 purpose and mutual-exclusivity rule are front-loaded, which is good, but the text balloons with internal artifacts that do not help an agent invoke the tool: review-ticket citations ('最終レビュー Important 7'), source file paths (`dcl/reader.py`), and upstream line counts ('上流 66,932 行'). The rationale for split tolerance windows is genuinely useful, but it is buried in an overlong aside.

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 and 10 optional parameters, so the description must describe returns — and it does: TSV with header, `total_score`-descending order, rank/ranked_by fields, explicit note that spectrum coordinates are excluded and live in `session.library.last_match`. Combined with the status-code taxonomy, nothing material is missing 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 does: it explains `spot_id` provenance, `arf2_path`/`dcl_file` fallback behavior, `ion_mode` case-insensitivity and accepted spellings, `rt`/`ion_mode` precedence over ARF2, the tolerance fallback chain with concrete defaults, and `top_n`'s default plus its undocumented negative-value behavior. Nearly every one of the 10 parameters is given meaning beyond its type.

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 states a precise verb and resource: match measured MS/MS from `.dcl` against a reference library loaded via `library_load`, returning top candidates. It also implicitly distinguishes itself from siblings by naming `library_load` as a prerequisite and `library_plot_mirror` as the downstream consumer of stored coordinates.

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 key usage constraint clearly — specify exactly one of `precursor_mz` or `spot_id` — and explains that `spot_id` can be obtained via `eic_search`, plus the `library_load` prerequisite. What it lacks is explicit routing against alternatives (e.g., when direct precursor-based matching is preferable to spot-based, or when to use `dcl_find_msms` instead).

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