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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description adds real context beyond them: interpretation semantics ('interpreted as pyteomics reads mzML') and validation provenance ('validated on every spectrum of three real runs'). It stops short of describing failure behavior on malformed input or memory/scale limits.

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-loads the action and resource, then lists the return fields compactly, ending with the downstream link to score_spectrum. The enumeration is dense but every clause carries information; no filler sentences.

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 an output schema present the return values need not be re-explained, yet the description accurately summarizes them, and it links to the consuming tool. Combined with rich annotations and full schema coverage, the definition is complete for correct invocation; only failure-mode behavior is absent.

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 100%, with id and msLevel already documented as filters, so the schema does the heavy lifting and baseline 3 applies. The description adds no additional param semantics (no mention of how id or msLevel interact, or the _subject/_files selection behavior).

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 (Read) and resource (spectra of a PSI mzML run file), then enumerates the exact fields returned (native id, MS level, centroid/profile, scan time, base peak, TIC, precursor, peaks). This clearly separates it from format siblings like read_mgf without requiring the schema to be opened.

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?

Gives clear context: it reads mzML and its MS/MS output is exactly what score_spectrum consumes as mz, intensity and precursorCharge, which routes the agent along a concrete workflow. It does not, however, explicitly state when NOT to use it (e.g. use read_mgf for MGF input), so no true exclusions are offered.

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