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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond that: cached from the daily board with no LLM and instant latency, pollable in a loop, $0.002/call, and a link to the Brier track record. Cost, freshness and latency disclosure are exactly the kind of behavior annotations cannot express.

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?

Purpose and routing are front-loaded before the output-field enumeration, and no sentence is pure filler. However, the middle clause is a long comma-spliced list of output fields that would read better structured, making it denser than necessary.

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, so the description carries the full burden of describing return values, and it does so comprehensively (oracle probability, 80% interval, market YES price, edge, cheap side, base rate, resolution date, sha256 commitment hash, sort order). Cost, caching and the sibling alternative are all covered, leaving nothing an agent needs to call it 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 coverage is only 50% (limit has no description), so the description must compensate. It defines edge as (p − odds), which gives min_abs its meaning ('Minimum |p − odds|'), and limit is a conventional result cap. The added context on min_abs is useful, though limit semantics remain unstated.

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 opening clause states a specific verb and resource: it surfaces open daily-board questions where a calibrated forecaster disagrees most with Polymarket. It is distinguishable from polymarket_top and polymarket_context, and it explicitly contrasts itself with oracle_forecast for single-question use.

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 states the condition for use ('list markets where the oracle and market odds disagree most') and names the alternative with its selecting condition ('for one new question use oracle_forecast'). It also tells the agent to poll it in a loop, so the invocation pattern is clear.

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