parlayapi_best_bets

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

With no annotations, the description carries the full behavioral burden and it delivers: it describes how the tool scans the whole board, uses the no-vig engine, filters to bets +EV at user-bettable books, ranks by edge, returns edge_alerts, and excludes certain bet types. It also notes the tool is scoped to the user's books. No annotation contradiction exists because there are no annotations.

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?

The description is structured well: a hook, a tight mechanism sentence, exclusions, and a parseable argument list. It is slightly verbose in its middle explanation but every clause adds useful behavior. It earns its length, but could be tightened.

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?

This is a read-only discovery tool with five params, many resulting context signals, and an output schema is present. The description covers scope, exclusions, ranking logic, parameter meanings, and how it differentiates from the closest sibling. An agent has enough to correctly select and invoke the tool without needing to ask about absent details.

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?

The input schema has zero inline parameter descriptions, so the description is the only source of parameter semantics. It provides a meaningful one-line gloss for all five parameters, including sport_key example, region options, books meaning, limit default, and min_edge semantics. This fully compensates for the schema's lack of documentation.

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?

The description opens with a clear question and answer: it ranks +EV plays for a sport. It explicitly names itself as the discovery counterpart to parlayapi_verdict and distinguishes its scope (player props, whole board) from that sibling (game moneylines). Specific behavior — scanning, grading, filtering, ranking — is front-loaded and leaves no doubt about purpose.

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?

The description gives strong context: use this for +EV player-prop discovery across the board, and explicitly excludes prediction markets and game moneylines, telling the agent to use parlayapi verdict for a line. It also states the output is scoped to user's books, which helps an agent choose this over alternatives.

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