gc_remind

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

With no annotations provided (no readOnlyHint, no destructiveHint), the description carries full behavioral burden. It states actions include delete and dismiss (implying mutation) but doesn't disclose whether reminders fire automatically, how state transitions between pending and fired work, or whether Eve-managed reminders behave differently from human-created ones. The 'managed by Eve or directly' hint adds context but not deep behavioral detail.

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 description is compact and front-loaded with the essential purpose ('Human reminders') followed by the action list. The 'Due accepts' line is useful. It could arguably drop the parenthetical explanations since the schema enums already cover those, but it's not bloated.

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?

As a 9-parameter multi-action tool with no output schema and no annotations, the description should carry more weight, but it covers the action semantics and due format. Missing: what the response looks like for list vs add, whether reminders persist across sessions, and how the recurrence field interacts with date-based firing. Given the tool's complexity (9 params, 5 actions), the description is adequate but leaves workflow questions open.

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 100%, so the baseline is 3. The description does not add meaning beyond what the schema already conveys—params like due, status, created_by, recurrence, snooze_for are all self-describing in the schema itself. The description mentions 'Due accepts: ISO timestamps, relative times' which slightly enriches the due parameter, but this is marginal beyond 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?

The description opens with 'Human reminders' and enumerates five distinct actions (add/list/dismiss/snooze/delete), giving a clear verb+resource+scope for what the tool does. It could distinguish itself more from siblings like gc_schedule or gc_beat, which may overlap in timing/cadence territory, but the reminder semantics are reasonably clear.

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 lists the actions and their purposes ('add (create reminder)', 'dismiss (mark as handled)', etc.), which implicitly tells agents when each mode is appropriate. However, it does not mention when to prefer this over alternative tools like gc_schedule, gc_timing, or gc_notify, nor does it state exclusion criteria for which reminder scenarios belong elsewhere.

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