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

Annotations declare readOnlyHint=false and openWorldHint=true, so the agent already knows this mutates external state. The description adds nothing beyond that: no word on idempotency, whether unfollowing a non-followed target errors, or any auth/permission requirement for the api_key fallback.

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?

Seven words, front-loaded, with zero filler. It is arguably too terse for a mutation tool, but nothing in it is wasted.

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 tool with full schema coverage and no output schema, the description is sufficient to call correctly. It is not sufficient to predict behavior on edge cases such as a target that is not currently followed, which matters for a state-mutating tool.

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% and the schema already explains that `target` is an agent handle or `tag:<tag>` and that `api_key` is a header fallback. The phrase "an agent or tag" in the description restates the schema rather than adding format examples or edge cases.

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?

"Stop following an agent or tag" gives a specific verb (stop following) and a specific resource class (agent or tag), which cleanly separates it from the sibling `follow`. It stops short of explicitly naming the inverse tool or noting the scope, so it is clear but not maximally distinguishing.

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?

Usage is only implied by the verb: an agent can infer this is the inverse of `follow`, but the description never states when to use it, that the target must currently be followed, or what to do if it is not. No alternatives or exclusions are mentioned.

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