explain_acmg_decision_path

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

Annotations already cover read-only/idempotent/no-destruction, and the description adds genuinely new behavior: the output is an ASCII rendering of the decision tree, the default is the germline ACMG verdict, and two somatic trees can be requested. Minor gaps remain — no mention of what happens when a variant hasn't been annotated yet or is unresolvable — but this is well beyond annotation coverage.

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 purpose, then the trigger condition, then the return format and defaults — a sensible order with no filler. The tree enumeration is stated twice (once in prose, once implicitly via the schema defaults), a small redundancy but not harmful.

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 needn't detail return values, yet it still characterizes the output shape (ASCII decision tree). Combined with the usage trigger and tree options, an agent has everything needed to invoke this correctly after annotate_variant.

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 baseline would be 3; the description adds the tree-to-version pairing ('germline' 2019, 'oncogenicity' 2022, 'acgs-uk-onco' 2025) and restates that variant accepts any notation annotate_variant takes. It does not resolve the edge case of passing tree='oncogenicity' while version defaults to '2019', which would be the one clarification that adds real value.

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 and resource ('explain step by step why each classification criterion did or did not apply') and clearly distinguishes itself from sibling annotate_variant by being the post-hoc explanation layer rather than the annotator. An agent can tell instantly what this produces: an ASCII decision tree of evaluated conditions.

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 sequencing ('Use after annotate_variant when the user asks "why was this classified that way?"') names both the prerequisite tool and the triggering user intent. It also states the default tree and which non-default trees exist, so the agent knows when to deviate from the default.

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