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

Annotations already declare this is a write (readOnlyHint=false), idempotent, and non-destructive. The description meaningfully adds the downstream effect that the schema and annotations cannot convey: the follow is persisted to the user's account and drives the For you feed and daily follow email.

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?

Three tight sentences with the usage trigger front-loaded, then input provenance, then the user-visible consequence. No filler and nothing repeated from the schema.

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?

For a two-parameter write tool with no output schema, the description covers trigger, inputs and resulting side effects adequately. It leaves auth/account prerequisites implicit ('saved to the user's account'), which is a minor remaining gap.

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 would be 3, but the description adds provenance semantics by telling the agent where valid type/key pairs come from (find_entities or get_entity), which reduces the risk of guessing an entity key.

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 (follow) plus the resource (a drug, gene, process, disease or other entity) and the effect, which cleanly separates it from the sibling 'unfollow' and 'list_follows'. An agent can identify the operation without opening the schema.

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 an explicit trigger ('when the user asks to follow...') and names the source of valid inputs (find_entities or get_entity). It does not explicitly name 'unfollow' as the inverse or state when-not to use it, so it stops short of full routing guidance.

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