Biggest resolved prediction-market surprises

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

Annotations already establish read-only, non-destructive, open-world behavior. The description adds genuinely useful context beyond them: no API key required, the sort direction, and two exclusion rules (multi-strike ladders, markets without provider resolution) that change what the agent will see. It does not cover rate limits or pagination behavior, so it falls short of a 5.

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 definition and definitional threshold, then terse supporting clauses. Every sentence carries information, though the definition sentence is dense and the closing 'No API key required' is a minor nicety rather than essential content.

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 an output schema present, the description needn't explain return shape, yet it helpfully clarifies the semantics of the surprise fields (winning outcome's probability, t7d often null). Combined with the annotations and exclusions, an agent has enough to call it correctly; only explicit sibling routing 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 description coverage is 100%, so the schema already documents all five inputs, making 3 the baseline. The description only marginally adds meaning by noting that window filters on resolution recency, which the schema already states. The field-level detail it provides concerns output fields (t24hProbability/t7dProbability), not input parameters.

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 states a precise verb+resource and defines the exact filtering and sort rule: resolved binary markets whose winner was priced under 50/100 at T-24h, ranked by lowest T-24h winner probability. This is specific enough to distinguish it from siblings like pm_data_resolved (all resolutions) and pm_data_disagreements. An agent can tell what this returns 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?

It explains the concept ('surprise index'), the window filter, and the exclusions, which implies when the tool is relevant (surfacing outlier resolutions). However, it never explicitly states when to prefer this over alternatives such as pm_data_resolved, pm_data_calibration, or pm_data_disagreements, leaving sibling routing to inference.

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