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

With no annotations, the description carries the full burden. It does usefully disclose ranking semantics (absolute blended-probability change), scope (active markets only), and operational facts (HTTP GET endpoint, $0.04 via x402). It does not cover rate limits, pagination, ordering ties, or the 1–50 limit ceiling's effect on results.

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?

Three tight sentences front-load the core definition, then the ranking rule, then the agent-facing value proposition; the bracketed endpoint/price/docs metadata is clearly segregated. Only mild redundancy between the first two sentences about probability moves.

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?

For a 5-parameter tool with no output schema and no annotations, the description covers the core ranking behavior and cost/access details adequately. It leaves gaps around segment vs. category precedence, min_liquidity semantics, and the shape/limits of the returned list, which an agent would need to call this confidently.

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 40%, so the description must compensate. It does add meaning for the window parameter by spelling out 1h/6h/24h and for limit indirectly via 'largest moves', but segment, category, and min_liquidity get no explanation, and the segment/category interaction is only documented in the schema text. Partial compensation, not full.

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 and operation: active markets ranked by absolute blended-probability change across selectable 1h/6h/24h windows, plus volume surge ratios. That is enough to distinguish it from level-oriented siblings like probability_board_* and probability_get. It does not, however, differentiate itself from the near-identical siblings probability_movers_delta, probability_movers_changes, and probability_movers-delayed, which an agent must disambiguate by name alone.

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?

There is a weak situational cue — 'the fastest way for an agent to find where news is landing' — which implies usage for news-driven discovery. But there is no explicit when-to-use statement, no when-not, and no routing to alternatives such as movers_delta or movers_changes. Usage is implied rather than prescribed.

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