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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds real behavioral context: ranking walks current public depth within the all-in budget, taker fees are estimated, and contracts with changed rules or unquotable size are omitted and reported unavailable. It doesn't describe ordering guarantees beyond 'rank' or the row shape, but the disclosure is richer than most.

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-loaded with the core action and outcome, followed by omission behavior, parameters, and the sibling router in a logical order. Slightly dense and repetitive between the 'where is it cheaper' sentence and the adjacent description of the per-row fields, but no wasted sentences.

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?

For a read-only listing tool with an output schema, the definition covers scope, fees, budget, omission semantics, optional filters, and the alternative tool. An agent has everything needed to select and invoke it correctly; return-value detail is correctly left to the output schema.

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 100%, so all three parameters are already documented, and the description largely restates side and family rather than adding syntax or semantics. It does clarify that family keys come from this tool's own output, which is a small value-add, but amount_usd gets no description-level treatment. Baseline 3 is appropriate when the schema carries the load.

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: ranks both sides across human-reviewed equivalent Polymarket–Kalshi pairs, with executable depth, taker fees, and the cheaper venue per row. It explicitly contrasts its job ('where is it cheaper to buy one side') with list_arbitrage_candidates, so an agent can route between them without opening either 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?

Gives a direct when-to-use trigger ('when the user asks where the largest currently executable cross-venue price differences are') and an explicit when-not with the named alternative for the opposite-sides/covered-payout case. 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.