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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety bar is low. The description adds genuinely useful behavior context: ambiguity is preserved rather than collapsed, predictions carry source and uncertainty, and EVE is license-gated. It omits caching/freshness behavior despite a freshness parameter, and says nothing about response size or pagination.

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?

Roughly four compact sentences front-loaded with the purpose, then defaults, then optional sections, then an id example. Dense but nearly every clause carries information; the linked guide reference is a small dangling fragment.

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 not be described, and the annotations cover the safety profile. Still, for a six-parameter tool with nested section sub-parameters and zero schema descriptions, an agent lacks enough to fill in freshness, assembly, or the civic/gwas/cbioportal sub-objects correctly.

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 0%, so the description must carry parameter meaning, and it only partially does. It gives an id format example and implies sources/sections via the defaults and predictions/eve mention, but leaves assembly, sections as a list, freshness, and the nested section_parameters (civic, gwas, cbioportal) entirely unexplained.

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 opening clause names a specific verb and resource ("Retrieve variant evidence") and adds a distinguishing scope qualifier ("assembly/transcript ambiguity preserved"). It is clearly a variant-evidence lookup rather than a generic fetch, though it never explicitly contrasts itself with siblings like get or query_source.

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?

It states which sources are included by default (ClinVar, population, CIViC) and how to opt into predictions (AlphaMissense) or EVE scores, which is real usage guidance. However, there is no when-not-to-use guidance and no routing advice against sibling tools such as get, query_source, or search.

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