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

Annotations only declare the generic mutation profile (not read-only, not idempotent, not destructive), while the description adds the operationally critical facts: it is simulated first, nothing is submitted until seller approval, and the live offer price is not changed by a proposal. It also supplies the stock range 1-255 and the no-VAT requirement, which the annotations cannot 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?

Purpose is front-loaded in the first clause, followed by required inputs, prerequisite ordering, then the simulation/approval safety note and supported-shop scope. Dense but nearly every clause carries operational information; the bracket prefix '[Campaigns]' is the only mild overhead.

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, and the description covers the mutation semantics, prerequisites, and approval gating thoroughly. The remaining gap is per-parameter coverage for the proposal item fields and campaign_id, which an agent must infer from the schema alone.

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 description coverage is only 33%, and the description compensates for the two most important item fields (sale_price is the campaign price without VAT; stock is the reserved piece count, 1-255) plus the need to solicit stock from the seller. However campaign_id, voucher_discount, max_qty_per_order, and the maxItems=200 batch cap are left undocumented in both schema and prose, so the compensation is partial.

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 products for a marketplace campaign') and immediately defines what a proposal is (sale_price without VAT plus reserved stock), which cleanly separates it from siblings like campaigns_check and campaigns_list. An agent knows this is the submission step for a campaign, not a listing or validation step.

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 clear context and routing: ask the seller for stock if missing, and if the campaign price is under the offer's minimum, call offers_update_price_limits first. It also flags the approval path via manage_action. It lacks an explicit 'do not use this when...' clause against campaigns_check, but the prerequisite chains are unusually explicit.

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