NFL Edge (model vs Kalshi)

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

Annotations already declare this a safe, non-destructive, open-world read. The description adds genuinely new behavioral context beyond them: it is a Pro-gated tool requiring sign-in with PredictionMarketsPicks or a Pro API key, and since there is no output schema it names the returned fields (model probability, price, edge, side). Rate limits or freshness caveats are not covered.

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 trigger use cases, then scope, then the watchlist and auth note; every sentence is doing work. The market list ('game positions, season win totals, MVP and championship odds') mildly duplicates the schema enum, keeping it from a 5.

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 4-parameter edge-scanning tool with no output schema, the description supplies the domain, the four market modes, the watchlist behavior, the returned edge fields, and the auth requirement. Coverage is strong; only explicit sibling routing and result-shape caveats are absent.

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%, so limit clamping, the market enum, minEdge units/defaults and ticker behavior are all already documented in the schema. The description largely restates the market categories and the tickers watchlist rather than adding syntax or edge-case detail, so the baseline 3 applies.

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 resource and operation: an NFL model compared against live Kalshi prices, covering game lines, win totals, MVP and championship markets, with model probability, price, edge and side. It is clear what the tool produces, but it never distinguishes itself from NFL siblings (nfl_prop_edge, nfl_ladder, nfl_power_ratings, nfl_win_probability), so an agent must infer the boundary.

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?

Opens with explicit trigger phrasing ('Use for "which NFL games are mispriced on Kalshi"...') and the market parameter routes between game/futures/mvp/championship modes, giving clear context for invocation. It stops short of naming alternatives or when-not conditions, so it lands at 'clear context, no exclusions' rather than full routing guidance.

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