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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true, so the safety profile is covered. The description adds real context beyond that: the write is scoped to email preference only, while follow status, list access, and bookmarks are unchanged, limiting the blast radius of the mutation.

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, front-loaded with the read/write purpose, then the consent and side-effect scoping. No filler; every clause carries a distinct constraint.

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 2-parameter tool with no output schema, the description covers purpose, the mutation trigger, consent scoping, and non-affected resources. It could note what the read returns or the handle format, but no output schema exists so return explanation is not required.

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%, so the description must compensate, and it does: `handle` is tied to a followed curator and `enabled` is framed as the email-preference toggle whose presence triggers a write. It stops short of stating the handle format or explicitly that omitting `enabled` selects read mode.

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+resource pair (read/set a followed curator's email preference) and disambiguates the write path via the `enabled` flag. It distinguishes itself from follow_curator by noting 'Follow is separate consent', though it does not name that sibling explicitly.

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?

Provides a clear gating condition for the mutation ('set `enabled` only on an explicit email request') and implies the read path is the default. It lacks explicit routing to alternatives (e.g., list_notifications for broader notification reads), but the when-to-write exclusion is genuinely useful.

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