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

Annotations already provide readOnlyHint=true and openWorldHint=true, so the bar for additional disclosure is lower. The description adds value beyond annotations by stating the output format (model probability, Kalshi price, edge, side, sorted by biggest edge first), requiring a Pro key, and guaranteeing that unsupported tickers return 'not_covered' rather than a fabricated edge. No contradictions with 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 a single paragraph of about five sentences with good front-loading of the core purpose. Every sentence adds information. It could be slightly more structured (e.g., bullet points for use cases) but is not verbose or wasteful. Gains a 4 for being efficient without being terse.

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 the moderate complexity (4 parameters, no output schema), the description covers what the tool returns, how to use parameter combinations (default vs tickers), and the prerequisite (Pro key). The annotations handle safety context. There is no missing critical detail that would prevent correct invocation, though a brief note on pagination or total result count would have pushed it to 5.

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 baseline is 3. The description adds meaning beyond the schema: it explains the 'market' enum values in plain language (e.g., 'game = this week moneyline edges'), describes how 'minEdge' is ignored when tickers[] is passed, and gives actionable advice for 'tickers' (pasting a Kalshi Pro watchlist). This elevates the score above baseline.

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 clearly states the tool finds actionable edges where the PredictionMarketsPicks NFL model disagrees with live Kalshi prices, covering specific market types (game moneylines, futures, MVP, championship). It uses strong verb+resource phrasing ("disagrees with live Kalshi prices — the actionable edge") and distinguishes from sibling tools like nfl_prop_edge and nfl_win_probability by focusing on model-vs-market edge across these categories.

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 provides explicit example use cases ('Use for...') and explains when to pass tickers[] (for specific Kalshi markets) vs using the default behavior. It also notes 'Pro key required' as a prerequisite. However, it does not explicitly mention when not to use this tool or suggest alternatives among the 22 sibling tools, so it lacks exclusions.

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