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

Annotations only declare read-only/no-destruct/open-world; the description adds genuinely load-bearing behavior: the complementary-binary assumption for the 'No' price, that fees can erase a spread and this is reported honestly via isArbitrage, and the critical caveat that the tool does not verify the venues quote the same bet. That last point is exactly the kind of limitation an agent must know before invoking.

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, then the convention assumption, then the return fields, then the trigger phrase and the caveat. Dense but every clause carries information; the parenthetical about the 'No' convention is long but necessary.

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 no output schema, the description carries the return burden and does so: it names isArbitrage, cost per $1 payout, guaranteed profit, ROI, and which side to buy where. Combined with the unverified-same-bet caveat, an agent has everything needed to call and interpret it.

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 the baseline is 3, but the description adds real meaning beyond the schema: feePctPerLeg's ability to flip isArbitrage to false, and the semantic intent of manualProbabilitiesPct (bypassing a live fetch). quotes/stakeUsd are largely restated from the schema, keeping this short of a 5.

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 ('checks 2-5 quotes ... for a guaranteed arbitrage') and pins the domain precisely: same real-world binary bet across prediction-market venues. It is unmistakably distinct from neighbors like run_prediction_market_edge or run_funding_arbitrage.

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 routes on user intent ('Use when user asks "can I arbitrage this bet across venues?"'), and clarifies the two mutually exclusive input modes (live quotes vs manual probabilities). It lacks an explicit when-not, but the scope is clear enough that an agent can pick it confidently.

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