ensembl_consequence

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

Annotations already declare readOnly and open-world, so safety is covered; the description adds genuine behavioral detail beyond that — automatic retry against the bare RefSeq accession when a version is stale, with the reinterpretation flagged in warnings, and invalid input surfacing the upstream VEP error explaining what could not be mapped. It also discloses the return payload (most severe consequence, per-transcript impact/codon change, SIFT/PolyPhen, co-located ClinVar/COSMIC/gnomAD data) with no output schema to do that work. Slightly short of a 5 only because rate limits or latency for on-demand VEP computation are not mentioned.

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-loaded with the capability that differentiates it, then organized into labeled input-forms / per-species / returns / alternative sections. Dense but every paragraph carries operational information; the parenthetical worked examples (mouse Trp53, human NM_ rejected by species 'mouse') are justified given how easy that misuse is.

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?

A three-parameter tool with no output schema, yet the description covers input syntax, species validity constraints, failure behavior, and the shape of the returned consequence data. Nothing an agent needs to invoke it correctly or interpret the response is missing.

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, but the description goes well beyond the schema for the two non-trivial parameters: it enumerates accepted variant syntaxes (c./p./g. HGVS with or without version, rsID), gives concrete examples, and states the per-species validity rule that NM_ accessions only work when the transcript belongs to that species. The 'limit' parameter is left entirely to the schema, which is the only reason this 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?

States a specific verb (predict functional consequence) and resource (variant), and immediately scopes it with two differentiators no sibling claims: works on novel variants absent from any database, and works for non-human species. An agent can distinguish it from variant_get and variant_search from the first sentence 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?

Explicit routing rules: prefer HGVS over rsIDs when both are available and explains why (dbSNP coordinate mapping yields less specific consequences); for known human variants prefer variant_get because it adds CADD/REVEL/AlphaMissense/ClinVar stars. Both the when-to-use and the when-to-use-something-else cases are named with reasons.

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