ariel_unfollow

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

Annotations already carry the safety profile (destructiveHint=true, readOnlyHint=false), and the description is consistent with them. It adds one useful behavioral detail — the follow record is resolved automatically from viewer state — which tells the agent the operation targets the viewer's own follow graph and needs no prior lookup. It does not disclose idempotency, error behavior when the actor is not followed, or reversibility. No contradiction with annotations.

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?

Two tight sentences with zero filler: the action comes first, the mechanism second, and each clause carries information an agent needs. Every word earns its place.

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 single-parameter mutation whose annotations cover the destructive profile and whose schema fully documents the parameter, this is nearly complete. The mechanism clause resolves the main ambiguity an agent would have — whether it must supply a follow-record ID. Minor gaps are the absent output schema, leaving return behavior unspecified, and no statement about idempotency or errors on a non-existent follow; both are low-stakes for such a simple 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?

Schema description coverage is 100%: the actor property is already documented as 'Handle or DID of the user to unfollow'. The description adds no param-specific syntax, format, or validation detail beyond what the schema provides, so on this dimension it contributes little. With full schema coverage, the baseline of 3 is appropriate.

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 action verb 'Unfollow' plus the resource 'a user' is specific and unambiguous, and it is naturally distinct from sibling tools like ariel_follow, ariel_unmute, and ariel_unblock. The second sentence adds mechanism detail about resolving the follow record from viewer state, which sharpens the picture. However, no sibling is named explicitly, so the agent must infer the distinction from the action verb alone.

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 context is implied: use this when the agent wants to end a follow relationship, and the 'Automatically resolves' clause signals that no follow-record ID needs to be looked up first. But there is no explicit when-to-use/when-not guidance, no statement of prerequisites such as whether the actor must currently be followed, and no routing to the inverse ariel_follow or to the similar ariel_unblock/ariel_unmute for contrast.

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