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 goes well beyond that by disclosing refusal semantics ('a build with no cached track is refused by name rather than answered empty'), provenance reporting ('every track answers with its authority, table and retrieval date'), coordinate convention, and the counting rule that balanced/unclassified variant types are never dosage evidence but are reported instead.

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?

Purpose is front-loaded in the first sentence, and the coordinate convention is placed last where it belongs. The first sentence is a long enumerated run-on that requires re-reading, and a few parentheticals ('the only case where a residue-level design is honest') are interpretive rather than operational, keeping it from a 5.

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 the description need not document return values, yet it usefully characterizes what each track reports. With 8 parameters (4 required), a nested _subject object and 100% schema coverage, the description plus schema give an agent enough to call the tool correctly; the missing piece is explicit routing against sibling region/variant tools.

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 100%, so the baseline is 3, and the description genuinely adds meaning on top: it explains that 'tracks' controls which of genes/dgv/segdups is read and that the coding verdict is coupled to the 'genes' track, and it restates the build-refusal behavior tied to the 'build' parameter. It adds little for the coordinate parameters beyond what the schema already says (1-based, inclusive), so it is not a 5.

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 description names a concrete verb ('say what a genomic region holds') and enumerates exactly what is returned: overlapping genes and RefSeq transcripts, contained complete CDS, DGV structural variants with frequencies, and segmental-duplication/paralogue similarity. That is far more specific than a restatement of the name. It stops short of a 5 because it never distinguishes itself from plausible siblings such as browse_region or lookup_variant, which an agent could reasonably confuse it with.

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 only implied: the agent can infer this is the tool for characterizing a coordinate interval, and the note that tracks defaults to all three and that the coding verdict comes with 'genes' guides how to scope a call. However, there is no explicit when-to-use versus when-not, no prerequisite statement, and no alternative sibling is named for region-level questions.

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