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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond annotations: the default sort order (most-due-soon first) and the fact that total is the full match count independent of limit/offset, which matters for pagination logic.

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 tight sentences with the resource, sort order and filters front-loaded, followed by the return-shape note. No filler or repetition of schema content.

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 an output schema present, return values need not be fully explained, and the description still highlights the total-count semantic. It stops short of clarifying due-window boundary behavior (inclusive/exclusive) or default page-size implications, minor gaps for a read-only list tool.

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 coverage is 67%; limit, offset, status and tenant_slug are documented in-schema, while due_after/due_before have no descriptions. The description's phrase 'due window' loosely maps to those two parameters but adds no syntax or inclusivity details, so it roughly matches rather than exceeds the 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 ('Paginated browse of the actor's reminders'), plus the scope (active tenant) and sort order ('most-due-soon first'). This clearly distinguishes it from kb_reminders_get, kb_reminders_cancel and kb_reminders_create among the siblings.

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 word 'browse' implies listing rather than fetching a single reminder, so usage is inferable, but no alternative is named and no when-not condition is given. An agent must reason from the sibling names (kb_reminders_get) itself.

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