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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered; the description still adds real value by disclosing that vig is computed from the market's own YES+NO prices rather than estimated, that ADI returns available:false because it has no live volume, and that vig is null for manual input. It also states what is out of scope (fees, slippage, order-book depth, correctness of the probability). It does not discuss rate limits or failure modes for network errors, which keeps this below 4 given the annotations already carry the read-only signal.

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-loads what it produces, then source rules, then edge cases, then returns; every block is purposeful despite the length. There is mild repetition between the "Edge cases" sentence and the later "Provide exactly one of probability/kalshiTicker/..." sentence, which restates the same exclusivity rule.

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?

No output schema exists, so the description enumerates the return fields (probability, decimalOdds, americanOdds, breakevenWinRatePct, vigPct, source, identifier, label) and adds the crucial instruction to read available first and discard all result fields when it is false. Combined with the edge-case rules and venue coverage, nothing an agent needs to call this correctly is missing.

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% and each property already explains its format and example, so the baseline is 3; the description goes further by imposing the mutual-exclusion rule ("give exactly one source, never none and never two" / "Provide exactly one of probability/kalshiTicker/...") and a tighter numeric bound (strictly between 0.0001 and 0.9999) than the schema's stated 0-1 range. Those constraints are not visible in the schema and prevent a malformed call.

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 and full output set ("Converts one probability into decimal odds, American odds, and breakeven win rate") plus the two input modes: manual probability or one live market. It explicitly separates itself from workflow.run_spread_reader for cross-venue comparison, so an agent can pick it without opening a schema.

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?

Gives concrete triggering phrasings ("what odds does a 35% probability work out to?", "what's the vig on this Kalshi/Polymarket/Limitless/Myriad market?") and names the alternatives with the conditions that select them: spread_reader for the same bet on several venues, window_fair_value for ADI theoretical pricing. Exclusions are explicit (one market, one venue per call; does not compare prices).

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