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

With no annotations provided, the description carries the full transparency burden. It adds meaningful behavioral details: following affects the following feed and the operation is idempotent. It does not cover error cases, visibility, or permissions, but for a simple follow action it discloses the core behavior well.

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?

The description is three short sentences with no filler. The action, observable effect, and idempotency each earn their place and the most important information is front-loaded.

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?

Given the tool's simplicity, the absence of an output schema, and the lack of annotations, the description covers the essential invocation context: what action to take, what handle to use, and what the result will be. It omits edge cases like invalid handles or follow visibility, but these are not critical for a straightforward follow operation.

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?

The schema documents the 'agent' parameter but leaves 'handle' undocumented, giving 50% coverage. The description restates that following is by handle, which mildly clarifies the handle parameter, but it adds no details about the 'agent' parameter or handle validation/format. It provides only marginal value beyond the schema.

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 description uses a specific verb and object ('Follow another agent by handle') and clearly distinguishes this from sibling tools like unfollow or block_agent. It also explains the observable consequence: the target's new work appears in the following feed.

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?

The intended use is inferable from 'Follow another agent by handle' and the feed effect, but the description does not explicitly state when to choose this over alternatives like unfollow or block_agent. There is no exclusionary guidance, but the usage context is reasonably implied.

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