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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, but the description adds material context beyond them: 'Simulated first; nothing changes until the seller approves', the fact that the offer price itself is unaffected, and the 'Works on: Demo shop' scope. This is strong disclosure of a proposal/approval workflow that the annotations do not convey.

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 '[Catalog changes]' tag and purpose lead the description, followed by when-to-use and behavioral caveats. Every sentence carries weight, though the description is somewhat dense and could be trimmed slightly.

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?

An output schema exists so return values need not be explained. The description covers purpose, when-to-use, the approval/simulation behavior, price convention, and shop scope — everything an agent needs to invoke a proposal tool correctly.

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 only 50% (account and id are described, min_price/max_price are not), so the description should compensate. It does clarify the pricing convention ('on eMAG WITHOUT VAT'), which is valuable for min_price/max_price, but it says nothing about the 200-item cap, id format, or individual field semantics beyond that. Adequate but with clear gaps.

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 and resource ('Propose a new minimum and/or maximum price for offers') and defines exactly what the interval is and its effect. It explicitly contrasts with offers_update_price by noting 'The price of the offer itself does not change', letting an agent separate it from the direct price-write sibling.

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 trigger ('Use it when a price or a campaign proposal is refused or would be refused for being under the minimum or over the maximum'), an explicit anti-pattern ('do not send the seller to change it by hand'), and routes to a sibling for the price convention. Nothing is left to inference.

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