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

Annotations declare destructiveHint=true and idempotentHint=false, but the description adds genuinely useful behavioral context beyond them: this is a merge-style partial update ('Anything left out stays') and it deliberately leaves customized users untouched. It doesn't cover permission requirements or immediacy of propagation, so it's not exhaustive, but it materially softens and clarifies what 'destructive' means here.

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 sentences, zero padding, with the core action (changing team defaults) front-loaded and the two key caveats (custom users unaffected, omitted fields preserved) following. Every clause carries information.

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 mutation tool with full schema coverage and annotations covering the safety profile, the description supplies the two nuances an agent most needs: team-wide scope and partial-update semantics. It omits error behavior and whether the change applies immediately, but no output schema is needed and the essentials are present.

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% and each nested object (kinds, quiet, digest, timeZone) is already documented in the schema, so the description carries no per-parameter burden. Its only param-relevant content is the collective partial-update rule 'Anything left out stays,' which matches the baseline 3 for a fully-covered schema.

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 and resource ('Change the notification defaults') and pins the scope ('everyone on the team starts with'), which implicitly contrasts with the 'my' siblings like update_my_notification_preferences and reset_my_notification_preferences. An agent can tell team-wide vs individual scope without opening the schema.

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 scope clause and the parenthetical 'people who customised their own keep theirs' tell the agent when this tool's effect applies and what it won't touch. It stops short of explicitly naming the individual-preference alternative, so it gives clear context without a full when-to-use/when-not-plus-alternative statement.

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