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 needs no repetition, and the description correctly does not repeat it. What it adds is domain behaviour: that DGV evidence is drawn from control populations and reported with frequencies, and that coding verdicts hinge on containment rather than overlap. It does not disclose the refusal-on-uncached-build behaviour or track-read defaults, though both are documented in the schema.

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?

It is a single front-loaded sentence that leads with the verb and then enumerates the four evidence types in a parallel structure, so it scans well and wastes little. The parenthetical about residue-level design is dense and somewhat opaque jargon, the one element that slightly dilutes an otherwise tight statement.

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 description need not explain return shapes, and it is complete enough about the evidence classes an 8-parameter, nested-object tool will surface. The remaining gap is routing context rather than content: nothing tells the agent how this differs from browse_region or from the record-level annotation tools in the same family.

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%, including the meaning of build, start/end coordinate conventions, the dosage enum, and the tracks list, so the schema does the parameter work and a baseline 3 applies. The description only implicitly maps its four output claims onto the three track groups (genes, dgv, segdups) and adds no format or syntax detail beyond the 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?

The description names a concrete verb ('Say what a genomic region holds') and enumerates the specific evidence classes returned: overlapping genes/RefSeq transcripts, complete CDS containment, DGV structural variants with frequencies, and segdup/paralogue similarity. That is far more specific than a restatement of the name. It never contrasts itself with near neighbours such as browse_region, lookup_gene, variant_consequences or auto_annotate, so an agent cannot route on purpose alone.

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?

There is an implied usage signal in the parenthetical that CDS containment is 'the only case where a residue-level design is honest', which tells the agent this call is a prerequisite check before residue-level work. However, there is no explicit when-to-use/when-not, no mention of the sibling that would be preferred for a plain region view (browse_region) or for annotation of a record (auto_annotate). Usage is inferable but not stated.

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