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

Annotations only declare the generic profile (readOnly=false, destructive=false, idempotent=false); the description adds substantive behavior: it is simulated first and nothing changes until seller approval, each proposal is capped by the workspace protection rule (50 default), remaining offers surface in warnings, and the rule can be raised in the dashboard. This is exactly the operational context 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 and the ids/from_days choice are front-loaded, and each subsequent sentence carries distinct operational guidance. It is dense and long, but the length is driven by real multi-round workflow detail rather than padding; minor tightening of the warnings/how-many-proposals passage would help.

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?

Given an output schema exists (no need to document returns) and the schema covers the remaining parameters, the description supplies everything else an agent needs: input mode selection, simulation/approval gating, proposal caps, warning-driven multi-round looping, and account scoping via list_accounts. Complete for a bulk mutation 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?

Schema coverage is 83%, so the baseline is 3, but the description adds real meaning by explaining the ids-vs-from_days routing and giving a concrete example ('from_days 6, days 3') that clarifies the days parameter's role. limit, account, and include_inactive are left to their schema descriptions, so it does not fully compensate beyond the routing logic.

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 handling time... on many offers at once' — and immediately scopes it as a bulk catalog change, distinguishing it from the single-offer siblings like offers_get or offers_update_price. The parenthetical defining handling time removes any ambiguity about the domain concept.

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?

Explicitly names the two mutually exclusive input modes (ids vs from_days) and tells the agent NOT to pre-list offers ('the tool finds them itself, do not list offers first'), which is a genuine when-not. It also prescribes the multi-round workflow: tell the seller how many proposals before starting, repeat after each approval until nothing remains.

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