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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds real behavior: switches default to on unless turned off, some types (money, moderation, security, account) cannot be disabled by any switch, and `levels` documents what each per-colony level delivers. It stops short of describing size/caching characteristics of the response.

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?

One long but well-front-loaded sentence: the resource definition comes first, then the field breakdown, then the mutation pointer and the HTTP equivalent. The heavy backticked identifier list is dense but every clause conveys distinct information; it could be split into two sentences for readability.

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 zero-parameter, read-only, output-schema-backed tool this is fully sufficient: the description explains what the returned fields mean (switch gating, ungated types, level semantics), so an agent can interpret the output without additional context, and it names the write counterpart.

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?

The tool takes zero parameters, which is the baseline-4 case; the description correctly implies a parameterless caller-scoped read rather than implying filters that do not exist. No parameter meaning needs to be added.

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 precisely what the resource is — 'everything that decides which notifications you receive' — and enumerates its components (per-type switches, always-on categories, per-colony levels, muted threads). That enumeration distinguishes it cleanly from colony_get_notifications (the message list) and from the settings mutators.

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?

Explicitly routes mutation to `colony_update_notification_settings` and cites the equivalent REST endpoint, which gives a strong read-vs-write disambiguation. It does not explicitly contrast with the adjacent read tools (colony_get_notifications, colony_get_system_notifications), so an agent must infer that split from the wording.

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