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

Even though annotations already mark this as read-only, the description adds meaningful behavioral detail: the model number is only published between 30% and 70% where calibrated, other rungs return the market only, and verdicts like PRICED and PARTIAL are defined. It also states 'Free, no key', giving the agent clear expectations about access and output semantics.

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 dense single paragraph but every sentence adds useful context, from the core resource to calibration caveats to example queries. It is longer than strictly necessary and could be broken into bullets, but it remains focused and front-loaded with the most important scope information.

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 no output schema, the description communicates what the agent will receive (Kalshi prices, distribution, verdict, ranking) but doesn't spell out the exact response shape. It also covers all important operational details for a read-only query tool, so it is reasonably complete for an agent ready to invoke it.

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 the baseline is 3, but the description adds real semantic value beyond the schema. It defines the meaning of the 'kind' values (SHAPE, LOCATION, PRICED, PARTIAL) in natural language and maps user intents to parameter combinations via the example queries. This goes beyond the simple enum descriptions in the schema.

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 names a specific resource (NFL strike ladders on Kalshi) and a specific action (compare Kalshi prices to a probability distribution, producing a verdict). It explicitly lists the covered families (spreads, season wins, player props) and distinguishes itself via the ladder/verdict concept, which sets it apart from sibling tools like nfl_edge or nfl_prop_board.

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 concrete example queries ('where does the model disagree with Kalshi on the Rams spread', 'which win-total rung is mispriced') that clearly signal the intended use case. It stops short of explicitly contrasting itself with sibling tools or stating when not to use it, so it doesn't earn a 5.

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