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

Annotations already establish this as a read-only, idempotent, closed-world lookup, so the description is not carrying that burden. It still adds real behavioral context beyond the annotations: the fallback to suggested_deals when a brand has no coupons, aliExpress-specific min_spend/ends_at fields, and the fact that only market 'us' is supported.

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?

The functional content is front-loaded and efficient, but roughly half the text is a 20-name brand enumeration and an 8-category list that an agent cannot act on. That inventory belongs behind list_brands, which the description itself already points to. Valuable guidance is diluted by reference data.

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?

There is no output schema, so the description must convey return shape, and it does: coupon vs promotion types, AliExpress tier fields, and the suggested_deals fallback. Combined with zero required params and a small flat schema, an agent has enough to call it correctly; only the limit/default behavior is left implicit.

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 75%, which already documents brand and market, so the bar is modest. The description adds substantial meaning beyond the schema: it explains that category only applies when no brand is given, that brand='aliexpress' unlocks a different response shape, and what those special-case fields contain. It says nothing extra about limit, which is the one documented gap.

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 states a specific resource and scope up front: verified, currently valid US coupons of type 'code' plus code-free 'promotion' entries. It also marks the sibling boundary by pointing at list_brands for the full brand list. It stops short of a crisp single-line definition because the defining sentence is buried under scope details.

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 spells out the branching conditions: brand optional, without brand you get newest coupons optionally filtered by category, 'aliexpress' returns its US code tiers, and a brand with no coupons falls back to suggested_deals. It also names the alternative (list_brands) for full coverage, so an agent can route correctly without guessing.

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