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

Annotations already establish the safe read-only profile (readOnlyHint, destructiveHint=false, openWorldHint), so the bar is lower. The description still adds a genuine behavioral rule absent from structured data: offers with no stated end date are never returned. It omits ordering, pagination, and the default window, keeping it from a 5.

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?

Two tight sentences with no filler, front-loading the trigger condition before the scope caveat. Every clause earns its place.

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?

Return values are covered by the output schema, safety by annotations, and the parameter by the schema, so the description only needs to add selection guidance and edge behavior — both present. It could be more explicit about the days window and sibling routing, but nothing essential is missing.

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?

The schema documents the single parameter (days, default 30, range 1-365) at 100% coverage, so the baseline is 3. The description adds nothing about the lookahead window or how days interacts with the results, leaving the schema to carry full param semantics.

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 title ("List bonuses expiring soon") plus the description make the resource and scope clear: it surfaces offers that are about to end. The description itself never restates the verb/resource ("lists bonuses within a lookahead window"), and it does not distinguish this from siblings like search_bonuses or compare_bonuses, so it lands just below the top.

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?

"Use when timing matters — a user asking what is about to end, or whether to act now" is an explicit, actionable when-to-use cue tied to user intent. It names no alternatives or when-not conditions, so an agent gets context but no routing exclusions.

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