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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds substantive behavior beyond that: the precise five classes of defect it detects, including that it re-derives translations from the record's own bases and genetic code rather than trusting the /translation qualifier. It does not say whether all findings are reported or only the first per CDS, but this is a modest gap.

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?

A single sentence front-loaded with the verb and object, followed by a colon-delimited list where each clause names a distinct check and nothing is redundant. It is dense but every clause earns its place; a slightly lighter framing (e.g. separating what is checked from how failures are reported) would read more easily.

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?

An output schema exists, so return values need no explanation, and the schema fully documents the three parameters. The remaining need is scope and preconditions, and the description covers scope well (all annotated CDS, one or many maps, uses the record's own genetic code) while leaving edge cases such as records with no CDS features or multi-record files unstated.

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%, so the schema already documents genbank, _subject, and _files, including the 'one string per file, a file may hold several records' nuance. The description only echoes the input concept ('one or more GenBank maps') without adding format, size, or selection detail, so it matches the baseline for a fully documented schema.

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 (check) applied to a specific resource (every annotated CDS of one or more GenBank maps) and then enumerates the exact failure conditions tested. This distinguishes it from build/annotation siblings such as auto_annotate or verify_construct, which do not perform per-CDS translation consistency checks.

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?

Usage is implied rather than stated: an agent can infer this is a quality-control step for annotated GenBank records, but there is no explicit 'use when' guidance and no mention of alternatives such as discover_annotation_contradictions, find_orfs, or verify_construct. There are also no stated prerequisites (e.g. that records must carry CDS features) or exclusions.

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