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

With no annotations, the description carries the full burden and does well: it discloses the owner-only permission gate, the default-off state, the email-only channel, the mailing-address dependency, and the do-not-email suppression. It omits what happens to already-queued reminders when disabled, but the mutation semantics are otherwise clear.

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 action and the lead-time semantics, then trimmed constraints as short clauses. Dense but every clause carries a constraint; the final sentence is slightly run-on where the two email caveats are chained together.

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 three-parameter settings mutation, the description covers permission, default state, range, channel, and the two customer-level edge cases that determine whether mail actually sends. An output schema exists, so the absence of return-value prose is not a gap.

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 0%, so the description must compensate, and it does: it maps 'on or off' to enabled, and gives the lead_days range (1-60) and a default of 14 that is absent from the schema, adding real value. shop_id is only implied by 'for the shop' and never explicitly explained.

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 pair (turn on or off) and a concrete resource (service-due reminder emails) scoped per shop, plus the extra knob for lead time. It does not name any sibling, so an agent must infer the boundary against services_*_Due and shops_setInvoiceReminders from the name alone.

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?

"Owner only" and "Off by default" give the caller prerequisites and the current state, which is useful context. However, nothing explains when to choose this over the adjacent shops_setInvoiceReminders / shops_setReviewRequest settings or the services_addDue family, so the selection logic is only implied.

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