scan_arbitrage_opportunities

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

With no annotations, the description carries the full burden. It usefully discloses that results are net of exchange taker fees and gas and that oracle risk is reported, which is real behavioral context. But it leaves out the operational profile: whether it queries venues live or from cache, scan latency/cost, data freshness, and whether results are ranked. For a potentially expensive cross-venue scan, that is a meaningful gap.

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?

Two dense sentences, zero filler, with the core action and the returned metrics both front-loaded. Every clause carries information an agent can use.

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?

No output schema exists, so the description's enumeration of returned metrics (net ROI, gross edge cents, combined costs, annualized yield, oracle risk) does real work in explaining the return value. What is missing is scope of coverage — whether all venues are scanned or only the exemplified pairs — and freshness, which matters for an arbitrage 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 description coverage is 100% with defaults, ranges and an enum on 'risk', so the schema already documents all four parameters well. The description's mention of net ROI is consistent with min_net_roi_pct but adds no syntax or interpretation beyond the schema. Baseline 3 is appropriate.

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 ('Find cross-venue matched prediction market arbitrage opportunities') and concretizes it with named venue pairs (Polymarket YES vs Kalshi NO). It also enumerates the metrics computed, so an agent knows this is an analysis/scan tool rather than a raw data fetch. It does not explicitly distinguish itself from siblings like search_prediction_markets or get_market_orderbook, but the arbitrage framing makes the difference inferable.

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?

Usage is implied by the examples and by the fee-adjusted ROI framing, which signals a screening/opportunity-discovery use case. However, there is no explicit when-to-use vs when-not, no statement of prerequisites (does it need a prior search? does it hit live orderbooks?), and no routing to the sibling tools an agent would need afterwards to inspect an opportunity.

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