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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the data source (Amazon's Promotions API), the 30-day lookback for ended promotions, that Amazon-reported problems are included, and that `narrative` carries the human-readable answer. It stops short of describing pagination or latency, which keeps it at 4 rather than 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?

Front-loaded with the core verb and resource, and the read-only limitation plus `how_to_create` fallback sit at the end where they belong. The middle sentence is a long dense list of returned fields that borders on run-on, but every clause carries distinct information.

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, and the description compensates by enumerating the returned data categories and flagging that `narrative` is the answer to surface. Combined with the explicit capability boundary (read-only), an agent has everything needed to call this correctly and to handle the out-of-scope case.

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?

Only one optional parameter (marketplace_id) with 100% schema description coverage, so baseline is 3. The description never mentions the marketplace scoping option, adding no semantics beyond the schema — though with coverage this high, that omission is low-cost.

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?

Names a specific verb and resource ('read... promotions from Amazon's Promotions API') and enumerates exactly what is returned: running/ending, scheduled/starting with event name, ended in last 30 days, discount, budget, SKUs, and reported problems. It is clearly separable from the sibling get_promotion_results, which implies performance data rather than a promotion inventory.

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?

Gives concrete trigger phrases ('what promotions do I have', 'when does my coupon end', 'is my Black Friday deal approved', 'why was my promotion rejected') and states the explicit when-not: AgentXray cannot create, edit or end a promotion, so the agent should say so and point the seller to `how_to_create` in Seller Central. Both the positive and negative routing are covered.

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