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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuine behavioral value by specifying what each entry contains — the next scheduled run, whether the last send succeeded and why not — plus deliverability status, which the agent could not know from structured fields.

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?

One compact sentence that front-loads the resource and then the returned fields. Slightly clunky grammar ('whether email reaches them now') but no wasted clauses.

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, the description carries the burden of explaining return values and does so adequately by naming the key fields. It stops short of covering ordering, volume, or whether reminders that never ran are included.

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%, so both instance_id and passport_token are documented in the schema itself. The description adds no parameter-level detail (e.g., scope of instance_id, or when passport_token is needed), 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?

The description clearly identifies the resource (your reminders to your human) and enumerates the salient returned fields (next_run_at, last result, email reachability), which distinguishes it from reminder_create/update/delete. However, it never states an explicit verb like 'list' and does not name the nearest sibling (schedule_list) that could be confused with it.

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?

There is no guidance on when to call this versus reminder_update or schedule_list, no prerequisites, and no exclusions. The only hint of intent is the parenthetical about email reachability, which an agent must infer is a diagnostic use case.

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