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

Beyond the annotations (idempotent, non-destructive, non-read-only) the description discloses the required 'account' scope and the free-plan quota of 3 follows, which are real operational constraints an agent needs. It doesn't say what a duplicate follow returns or what side effects appear in list_follows, leaving some behavior implied.

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?

Dense, front-loaded, and free of filler: the action, the lookup tool, the quota, and the scope each occupy one short clause. The trailing 'Free.' duplicates the free-plan quota sentence and is the only wasted token.

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 one-parameter mutation with no output schema, the description covers the value source, the permission scope, and the plan limit, which is most of what an agent needs to call it correctly. Only error/limit-reached behavior is unaddressed.

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 0% and the single 'person' parameter is an undocumented string, so the description's clarification that the value is a slug and can be discovered via find_people carries meaningful weight. It still gives no format example or length guidance against the 60-char cap.

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 ('Follow a person by slug') and anchors it to a known UI behavior ('as the Follow button does'), which separates it from unfollow_person and follow_podcast. It doesn't explicitly name unfollow_person as its inverse, so it stops short of full sibling differentiation.

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?

Points to find_people for obtaining the slug and gives the concrete condition that constrains use on the free plan ('follows up to 3'). It doesn't state what happens when the limit is reached or how to unfollow, but the practical when-to-use context is clear.

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