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

Annotations declare non-idempotent and non-destructive, but the description adds the consequence ('calling it twice creates two reminders'), the delivery semantics (nothing sent when due), closing behavior, assignment semantics for personal vs workspace keys, and the lead-parking side effect with reasonText in lead history. That is substantial context no annotation field carries.

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 what it is and the idempotency warning, and each sentence carries information. It is dense and somewhat long, with several clauses chained by semicolons, but nothing reads as filler.

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?

For a mutating, non-idempotent tool with no output schema, the description covers side effects, result shape on the lead path, permissions/assignment behavior, and lifecycle. An agent can call it without discovering these behaviors at runtime.

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 a baseline of 3 applies. The description earns a bump by tying reasonText to lead history when leads are on and explaining that the result may return task null, meaning the caller's assumption about a created task can be wrong even with valid 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?

The first sentence names a specific verb and resource (create a follow-up reminder for a person) and scopes it to contacting a person. It is immediately distinguishable from send_message and broadcast, both named later, and from the automatic 'no reply for N days' follow-ups.

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?

Explicitly routes the agent: 'use send_message or a broadcast to actually message someone' versus this tool which sends nothing. It also states the reminder stays open until completed, and that replies do not close it, which is exactly the exclusion an agent would otherwise get wrong.

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