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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is the domain filtering rules: hidden-sphere tasks are dropped, their count surfaces only as hidden_from_day in today_total/today_done, and a hidden task with time plus reminder still appears marked hidden_from_day. It also flags a follow-up behavior (ask what got done on expired open tasks), which is real behavioral context beyond the annotations, though the field names it references are never defined as a return shape.

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 return contents are front-loaded, but the middle sentences are overloaded run-ons ('out of today_total and today_done, only their number shows as hidden_from_day') that take rereading. The get_tasks pointer is repeated twice ('see get_tasks' and 'get_tasks lists them'), which is avoidable redundancy.

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 and no parameters, the description carries the burden of describing returns, and it largely does so: date, goal, streak, tasks/subtasks, and the hidden_from_day counter behavior. What's missing is a coherent field list or ordering, so an agent knows the concept but not the exact shape it will receive.

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 (100% schema coverage, empty object schema), so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly introduces no phantom inputs.

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 enumerates exactly what the tool returns: the user's local date, main goal, day streak, and today's tasks with subtasks. It also scopes the resource against the sibling by noting that hidden-sphere tasks are excluded and that get_tasks lists them, so an agent can distinguish it from get_tasks without opening either 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?

It states a clear trigger ('Fits when the user asks about today or a relative date needs resolving') and routes hidden-task lookups to get_tasks. It stops short of a full when-not list or mention of siblings like get_day_brief or show_day, which an agent would have to disambiguate on its own.

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