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

Annotations cover the safety profile (readOnly, non-destructive, closed-world), and the description adds material context they cannot: a 10-credit cost, the closing-by-default vs opening behavior, the 2023-2025/6-book data boundary, and a compliance rule against computing stakes, payouts or recommending bets. That last constraint is genuinely decision-relevant and unobtainable from structured fields.

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 'Use for...' clause, then layers coverage, defaults, parameter semantics and the compliance caveat in a dense but readable block. The inline price examples ('KC -10.5 at +260') are illustrative but add length; nothing is outright wasted.

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?

Given an output schema exists, the description need not explain return shapes. It still covers market scope, snapshot default, book coverage, credit cost and the market-information caveat, which is everything an agent needs to invoke this correctly.

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%, including defaults for snapshot_type and market, so the baseline is 3. The description mostly restates those defaults ('closing... last before kickoff') and then discusses 'side' (home/away, over/under) and 'point', which are not parameters in the schema at all — useful for interpreting results but not a parameter contribution.

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 precise verb+resource+scope: alternate spreads and totals per sportsbook, down to 'every point on each book's ladder with its price'. The word 'alternate' implicitly separates it from main-line odds tools like get_odds or get_line_movement, so an agent can route without opening a 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?

'Use for alternate spreads and totals by sportsbook' plus the game/season/book coverage gives clear context for when this tool applies. It does not, however, name the sibling to use for main lines (get_odds) or state exclusions, so it stops short of full when/when-not guidance.

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