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 partly covered. The description adds real value beyond them by disclosing the dual-mode behavior (parameter-driven read vs write) and by bounding the blast radius ("Never changes access, saves or follows"), which meaningfully narrows what destructiveHint=true might otherwise imply.

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?

Three short sentences, front-loading the read behavior before the write behavior, with no filler. Each sentence carries a distinct fact (read trigger, write requirement, scope limit). Slightly terse for a dual-mode mutation tool but not padded.

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?

With no output schema, the description is not required to explain return values, and the annotations cover the mutation safety profile. It covers mode-switching and change scope, which is what an agent needs to invoke it correctly; the main gap is the lack of any guidance on the related curator_notifications sibling.

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 only 33% (only `list` is documented in the schema), so the description must compensate, and it does: it explains that omitting both `push` and `email` switches the tool into read mode, and that supplying them sets those channels. This gives the two boolean parameters semantics the schema lacks, though it doesn't state accepted values or defaults beyond the on/off implication.

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 states specific verbs and a resource: it reads all notification settings when push/email are omitted and sets push/email new-pick notifications for one list. This resolves the ambiguity created by the name 'list_notifications' (which reads like a pure list operation) versus the title 'Set new-pick notifications'. It does not, however, distinguish itself from the sibling tool curator_notifications, nor explain how they differ.

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 gives an explicit trigger for the read path ("Read every notification setting when `push` and `email` are omitted") and an explicit constraint on the write path ("Only on an explicit request, set..."). That is clear when/when-not guidance, but it never names an alternative tool or scope for when a different notification tool should be used instead.

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