Follow user

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-structured context: this is a public social action ('They see the follow') and that the tool is bidirectional via the unfollow flag rather than being a separate endpoint. It does not mention auth or rate limits, but nothing important is contradicted.

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?

Front-loaded with the core action and effect, and kept to three short sentences. There is mild redundancy between 'Follow or unfollow' in sentence one and 'or unfollows them' in sentence two, which repeats rather than adds.

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, non-destructive, idempotent action with a fully documented schema and no output schema, the description covers purpose, effect on the caller's feed, and the distinction from email subscription. Only edge behavior (e.g., already-following) is left implicit, which the idempotentHint already implies.

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% — the schema already documents 'user' as a handle or user ID and 'unfollow' as a boolean defaulting to false. The description reinforces that unfollowing is the same operation in reverse, but adds no format, lookup, or error semantics beyond the schema. Baseline 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 description gives a specific verb+resource ('Follow or unfollow a Substack user') and states the effect ('so their Notes reach your feed'). It also distinguishes the action from the nearest conceptual sibling — subscribing — which an agent would otherwise confuse with add_subscriber.

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?

It states the condition for use (get their Notes and activity in the app) and explicitly excludes the adjacent alternative: 'Following is not subscribing: you get their Notes and activity in the app, not their newsletter by email.' The relation to the Follow button on a profile gives an agent a concrete mental model.

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