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

With no annotations supplied, the description carries the full behavioral burden, and it does disclose a non-obvious side effect: a snooze time landing inside quietHours gets pushed to the end of quiet hours, and the response gains a quietHoursAdjusted field. It also tells the agent it must relay that adjustment to the user. What is missing is the permission or error profile and whether an existing snooze is overwritten.

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 effect, then the recurrence scoping, then the quiet-hours edge case and the reporting duty. Every sentence carries information, though the heavy parenthetical stacking makes it denser than it needs to be.

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 three-parameter mutation with no annotations and no output schema, this covers the core behavior, the one surprising edge case, and the one response field an agent must act on, which is the right prioritization. The Account-vs-TODO timeZone inconsistency and the absence of error or permission context are the remaining gaps.

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 schema already documents until and occurrenceDate (67% coverage), but the description adds real meaning: occurrenceDate is not merely 'which occurrence' but explicitly limits the snooze to that single recurrence, and until is interpreted in the TODO's clock rather than a generic one. Note a discrepancy, however: the schema says the wall-clock form is in the Account timeZone while the description says the TODO's timeZone, which could mislead a caller.

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?

Names a specific verb-effect (suppress notifications until a timestamp) on a specific resource (a TODO), and immediately scopes it to a single recurrence by way of occurrenceDate. This is clearly distinguishable from add_todo / complete_todo / update_todo, so an agent can route correctly 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 description makes the calling context concrete: supply a wall-clock or ISO8601 timestamp, and for recurring TODOs pick the occurrence via occurrenceDate. It even says where to look for quiet hours (get_me). It stops short of naming when a caller should prefer update_todo, or what happens if the TODO is already snoozed.

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