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

Adds substantial context beyond annotations: costs 5 credits, an empty slate costs nothing with an explanatory note, a failed call is free, and it clarifies the accuracy/backtest note is not a live record. This is exactly the kind of cost and failure-mode detail annotations cannot convey.

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 scope, then cost/failure behavior. Dense but each clause carries useful information; slightly long but no filler sentences.

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?

With an output schema present, return values need no explanation. The description covers cost, empty/failure behavior, exclusions, and staleness notes, leaving no gaps for correct invocation.

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?

Zero parameters, so baseline is 4. The description reinforces this with 'Takes no arguments (current slate only)', removing ambiguity about scope.

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+resource ('win probability for each NHL game on the current slate') and enumerates the returned fields (home/away probability, A/B/C grade, start time, model version, generation time). Explicitly distinguishes itself from odds-based siblings by stating no odds, prices, or goalie/injury notes are included.

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?

Clear context: use for the model's own win probabilities on the current slate, no arguments, current slate only. It implicitly routes away from odds/pricing tools by naming what it does not contain, though it does not name a specific sibling alternative.

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