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

The readOnlyHint annotation is not blatantly contradicted because the tool "prepares" decodable steps rather than executing them, but the wording "decrease every still-active sale rate" describes an on-chain state mutation that is never reconciled with that read-only hint. The description would be much stronger if it stated plainly that it produces unsigned calldata and does not broadcast, and whether any approvals or follow-up execute call is required.

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?

A single front-loaded sentence with no filler paragraphs; the effect is stated before the mechanism. It leans slightly on vague qualifiers ("complete", "still-active") that carry meaning the rest of the definition never pins down.

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, but for a six-required-parameter mutation-preparation tool awash in similarly named siblings there are real gaps: how the caller obtains the order list, what makes an order "still-active" (presumably end_time vs pending_timestamp), and whether zero-rate orders must be excluded.

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. The description does add meaning for the orders array by tying it to "selected orders" and active sale rates, but it says nothing about pending_timestamp, sender, token_id, or the nesting of order_key/end_time that determine which orders count as still active.

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?

A specific verb ("Prepare") plus resource (TWAMM order stop flow) with the concrete effect spelled out: collects selected orders and decreases still-active sale rates into decodable steps. It stops short of distinguishing itself from the closely named siblings prepare_twamm_order, prepare_twamm_order_collection, and prepare_twamm_virtual_orders, so an agent must infer the boundary from the name alone.

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?

The phrase "every still-active sale rate" implies a precondition (only active orders are touched) and "one atomic batch" implies batching semantics, but there is no explicit when-to-use vs when-not, no mention of whether this must be followed by a commit/broadcast step, and no guidance on choosing among the three other prepare_twamm_* siblings.

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