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

Annotations already flag destructive=true/openWorld=true, and the description adds real behavioral context beyond them: the preview (before→after) vs apply semantics, the approval requirement, and the pricing invariants (delta below Buy Box, never below floor). This is exactly the mutation-specific detail an agent needs before a destructive write.

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-loads 'ACTION' and the core purpose, then the mechanism, then the confirm contract and safety directive, in four tight sentences. No filler; each clause adds an actionable fact.

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?

With no output schema, the description correctly explains the return shape (preview before→after) and the write behavior. It leaves the confirm_id token round-trip and multi-SKU/error behavior to the schema, which is a minor gap for a destructive tool.

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?

With 83% schema coverage the baseline is 3, and the description elevates it by defining delta relative to the Buy Box and floor as a hard minimum, plus confirm's two-state behavior. It does not address account_id or the confirm_id round-trip flow, which the schema carries (partly in Italian).

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 ('Reprices') and resource ('the given SKUs to win the Buy Box') and explains the mechanism (compare to Buy Box, propose delta below, never below floor). This clearly distinguishes it from sibling read tools like get_buybox_prices and generic writers like bulk_update_prices/update_price.

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 an explicit two-phase workflow: confirm=false for a preview, confirm=true to apply, plus the directive to always show the preview and obtain explicit user approval. It does not name sibling alternatives (e.g., bulk_update_prices) so the agent must infer this is the buy-box-specific path, but the mode-selection guidance is strong.

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