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

With zero annotations, the description carries the full burden of behavior disclosure and does so: it names the delivery channels (official DM, optional App push), the default preview mode, a frequency-control constraint, and the confirmation protocol requiring the same parameters plus hash. It also explicitly disclaims SMS and states that submission or attempted push does not mean delivery or read.

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?

Information density is high and the critical precondition is front-loaded in the first clause. The semicolon-separated telegraphic phrasing is efficient but a bit dense, with the purpose clause buried mid-sentence.

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 messaging/mutation tool with no annotations, no output schema, and five parameters, the description covers eligibility, the two-phase confirm flow, exclusions, and outcome caveats well. It leaves the preview response format and the effective reminder content unstated, which matters for an agent composing the confirmation step.

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 0%, so the description must compensate, and it partially does: it explains that preview defaults to true and that previewHash must accompany the same parameters on the confirmed execution. It does not explain what target's member/counterpart values mean, nor conversationId or organizationId, so three of five parameters remain undocumented.

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 makes clear this performs a preview-then-send reminder to a follow-up target over the official private-message channel, with optional App push. The verb is implied through the mechanics rather than stated outright, and no sibling (list_host_followups, log_host_followup, set_host_followup_done) is named to differentiate scope.

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?

It states concrete prerequisites to call it: the user must be logged in, be the current host, and the AI must have judged the target WORTH_CONTACT. It also gives an explicit exclusion rule — declined, withdrawn, or closed follow-ups cannot be reminded. The only gap is that no alternative tool is named for finding eligible targets.

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