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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: a 10-credit per-call cost with refund when a game has no lines, estimate_only to preview price without being charged, historical coverage windows (May 2023 / October 2023, larger books only), the fact that most books were captured once so opening and closing are often identical, that not every game has every market, and the semantic of negative minutes_before_start. It also states a hard usage restriction against computing stakes/payouts or recommending bets.

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 purpose and market scope, then parameters, then return shape, then coverage windows, cost, and the sibling alternative. Nearly every sentence earns its place, but the whole thing is delivered as one dense block, and clauses like the aside on sportsbook-listed start times add length without changing agent behavior.

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 high-complexity, credit-charging, historically bounded odds tool, the description covers cost and refund behavior, coverage windows, sparsity of markets, capture semantics for opening/closing lines, the low-cost estimate path, the correct sibling for full-game markets, and the compliance restriction on betting advice. With an output schema present it does not need to explain return values in detail, and what it does say is sufficient.

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 game_id, market enum values, bookmaker and estimate_only are all already documented in structured form, and the description largely restates them ('Pass game_id... and market', 'Set estimate_only to get the price without being charged'). It adds only marginal semantic value, such as clarifying the 0.5 total as the no-run-first-inning market, which the enum description also covers. Baseline 3 is appropriate when the schema carries the parameter burden.

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 ('Use for the extra betting markets of a game as history') and enumerates exactly which markets it covers (first 5 innings winner, run line, total, 1st inning total and three-way result). It then explicitly contrasts with the sibling that handles full-game markets: 'For the full-game moneyline, spread and total use get_odds.' An agent can distinguish it from get_odds 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 explicit entry conditions ('Pass game_id (from get_games or get_schedule) and market'), names the alternative tool and the condition that selects it ('For the full-game moneyline, spread and total use get_odds'), and describes the estimate_only path for pricing a call before paying. Nothing about when to choose this versus siblings 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.