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

Annotations only flag it as a non-read-only, non-destructive, non-idempotent write; the description adds real context: the record closes the reminder, sent_at must be the actual send day rather than today's default, and the reason feeds the next draft. It does not address what happens on a repeat call or on an already-closed reminder, leaving the non-idempotent hint unexplained.

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?

Front-loaded with the core action, then branch semantics, then effects. The client-embarrassment line is colorful but earns its place as a guardrail against fabricated sends; the whole thing is slightly prose-heavy for a four-parameter tool.

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?

No output schema exists, so the description carries the return behavior, which it does with 'Effects: reminder closed as sent or discarded.' Remaining gaps are edge cases: behavior on an already-closed reminder and whether the reminder_id must exist.

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 3 is the baseline, but the description goes beyond it: it clarifies that sent_at is the day it actually went rather than defaulting to today, and that reason exists for whoever drafts the next reminder. That is meaningful added semantics for two of the four parameters.

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: record a reminder's outcome as sent (with when) or discarded (with why), and closes with 'Effects: reminder closed as sent or discarded.' That distinguishes it from drafting/getting siblings, though no sibling is named explicitly to route the agent.

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?

Gives clear when-to-use per outcome branch (SENT = they told you they sent it; DISCARDED = they decided against it) plus an explicit when-not: 'Never record a send nobody told you about.' It lacks a pointer to the alternative tool (e.g. solo_draft_reminder) for the drafting case.

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