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

With no annotations, the description carries the full load and does it well: it discloses the mid-flight interruption path ("if another session is running, the Mac asks them before switching") and that a pre-focus ritual may open first. It omits what the tool returns or how failure (e.g. task not found) surfaces, which keeps it off a 5.

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?

The core action is front-loaded in the first clause, and the remaining sentences carry real information (switching prompt, ritual, consent). The nested parentheticals and repeated "as their Focus on this button does" phrasing add slight density but no waste.

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 two-parameter, no-output-schema tool, the description covers the action, the interruption semantics, and the consent precondition — enough to call it correctly. Missing only outcome/error behavior, a minor gap given the schema already documents both parameters.

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 the schema already explains that `task` accepts an id or a uniquely-matching title and that `minutes` ranges 5–240 with a task-length-then-25 default. The description adds no parameter detail beyond restating "one of the user's tasks," so the baseline 3 applies.

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 ("Start a focus session on one of the user's tasks in Caddie on their Mac") and clarifies the exact UI affordance it mirrors ("the notch's timer and check-ins"), which removes ambiguity about scope. No sibling does anything similar, so no differentiation is needed, but it also never explicitly says so.

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?

"Only when they asked for it, or agreed" is an explicit gating condition that tells the agent when it may invoke this tool — unusually strong consent guidance for a mutation-style action. It does not name alternatives or when-not-to-use beyond the consent rule, which is acceptable given no sibling overlaps.

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