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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds useful semantic context about the ROLE relationships and authoritative nature of the response, but says nothing about pagination, response size, or traversal depth for a graph-walking read.

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 core action and authoritative scope, then usage. Dense with parenthetical examples, but each earns its place by clarifying the return semantics; no filler sentences.

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 no output schema needed, the description fully covers purpose, relation kinds, and when to reach for it; annotations carry the safety profile. An agent has everything required to call it 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 100%, so the schema already documents code, kinds, and terminology thoroughly. The description reinforces what the relation kinds mean but does not add syntax or default details beyond the schema, which is the expected baseline when the schema does the heavy lifting.

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 ('Walk') and resource (NCIt hierarchy and relationship graph around one concept code), and names the exact relation types it returns (parents, children, roles, associations). This clearly distinguishes it from evs_concept and evs_search_concepts in the sibling list.

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?

Gives a concrete use case: 'expand a disease or drug into its subtypes before querying trial or genomic data,' and explains what each relation kind answers ('what is X a kind of', 'what kinds of X'). It stops short of naming a sibling alternative or stating when-not to use it.

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