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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds genuine behavioral context by disclosing the per-item result discriminator ("success" LMSR vs "orderbook" CLOB vs "error") and explaining why orderbook markets return bestBid/bestAsk/spread/mid rather than a single price. It also notes no idempotency key is required, which is a useful confirmation though partly redundant with idempotentHint. It does not discuss partial failure handling beyond the "error" type or ordering of results, so it stops short of a 5.

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 the batch size and call semantics in the first sentence, then unpacks the three result shapes, then closes with the read-only/no-idempotency-key note. Every sentence carries information; the parenthetical about LMSR pricing against a resting book is a dense but legitimate rationale rather than filler.

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 an output schema present the description need not document return values in detail, and it correctly spends its budget on the one thing the schema cannot convey: the polymorphism of the per-item result. Annotations cover the safety profile. The remaining gap is practical invocation context — whether partial failures fail the whole batch, and when to prefer a single-quote call — which is minor but real.

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?

Reported schema description coverage is 0% at the top level and the description says nothing about the `items` array contents — no mention of side, amountIn, tokensIn, marketAddress, or the buy/sell discriminant. The nested item schema and $defs do carry extensive prose documenting these fields, so the agent is not left stranded, but the description itself contributes zero parameter meaning beyond the 20-item cap.

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 (Get), a specific resource (trading quotes), and a scope (up to 20 in one call) that cleanly separates it from the single-quote sibling kellian_get_quote and from the orderbook-batch sibling. An agent can tell what it returns and how many without opening the schema.

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 "Read-only planning helper" implies the usage context (pre-trade planning, not execution), but there is no explicit when-to-use / when-not-to-use guidance and no named alternative (e.g. kellian_get_quote for a single quote, kellian_prepare_trades_batch for turning quotes into orders). Usage is inferred rather than stated.

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