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

Annotations only declare readOnly/openWorld=false/non-destructive; the description adds substantial non-annotation context: it computes terminal distribution only (not first passage/touch), uses a 365-day year convention, and requires volatility as a manual input because there is no live implied-vol market for these contracts. Those are exactly the assumptions that would otherwise cause silent misuse.

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 core purpose and the payout definition, then usage, then returns — a sensible order with no filler sentences. The venue-naming parenthetical ("the shape ADI Predictstreet and Kalshi-style...") is slightly verbose and could be trimmed without losing meaning.

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?

There is no output schema, but the description enumerates the returned fields (d1, d2, probAbovePct, probBelowPct, fairPriceAboveCents, fairPriceBelowCents) and their convention. Combined with the model assumptions and the manual-vol caveat, an agent has everything needed to call and interpret this tool correctly.

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 baseline is 3; the description earns extra credit by explaining that volatilityPct has no live source and must be supplied manually, and by clarifying the cents convention that makes outputs directly comparable to venue quotes. It does not elaborate on how minutesToClose interacts with the annualization beyond the 365-day note, leaving a little on the table.

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?

Names a specific verb (price/theoretical fair value) and a precise resource (time-windowed crypto up/down cash-or-nothing digital contract), and pins down the exact model used (N(d2)). It explicitly delimits itself from adjacent concepts: probability at close only, not first-passage/touch probability. An agent can distinguish this from run_black_scholes, run_black_scholes_live, and run_market_implied_odds without opening the 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 an explicit when-to-use condition ("no live market price to read... e.g. a venue's contract has real terms but zero trading volume") and an explicit alternative class to use instead (a live-market odds tool). It also provides two concrete user-phrasing triggers ("what should this up/down contract be worth?", "fair probability BTC finishes above $X in N minutes").

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