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

No annotations are provided, so the description carries full disclosure burden. It transparently explains the selection algorithm, the non-nested constraints (per-exhaustive-outcome pricing), the risk caveat, and the disabled-result behavior when the feed key is missing. This is strong behavioral transparency for a no-annotation tool.

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?

Four sentences, each adding distinct value (scope, algorithm, caveat, edge-case behavior). Front-loaded with the primary purpose. No wasted words, though the algorithm sentence is dense and could be slightly verbose.

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-format explanation isn't strictly required. The description covers scope, algorithm, risk caveats, and edge-case feed-disabled behavior. For a tool with 2 params and defaults, this is thorough. Minor gap: no mention of how many events are returned or any pagination.

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 0%, so the description carries the full burden. sport_key and capital_usd have defaults in the schema but no semantic explanation. The description mentions stakes and payout which relate indirectly to capital_usd, but doesn't explicitly define the role of either parameter. However, with defaults present and the tool's purpose clear, the param usage is reasonably inferable.

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?

Clear verb+resource: 'Find unfilled sportsbook surebet candidates across the configured live books.' Distinguishes from sibling list_arbitrage_candidates by specifying sportsbook-specific context and the well-defined selection algorithm (Σ(1/odds) < 1, cent-rounded stakes, worst payout).

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?

States the event scope (two-way or three-way h2h events) and the exact mathematical filter used. Explicitly warns profit is not locked unless every bet is accepted, which gives the agent clear context on reliability. Lacks explicit when-not-to-use vs alternatives like list_arbitrage_candidates, but the sportsbook-specific framing establishes clear context.

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