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

No annotations are provided, so the description carries the full behavioral burden. "Ranked by |delta|" is genuinely useful ordering information, but the description never states that this is a read-only query, whether resolved/illiquid markets are excluded, how ties are broken, whether results are truncated at top_n, or any rate/auth constraints.

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?

Two short sentences, front-loaded with the resource and immediately followed by the ranking rule — no filler or redundancy. It is efficient, though the extreme terseness leaves valuable detail on the table for a 5-parameter tool.

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 five parameters, 40% schema coverage, no annotations, and no output schema, the description is too thin. An agent must guess at the direction semantics, category values, top_n behavior, and the shape of returned mover records.

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 only 40% (from_ms and to_ms documented; top_n, category, and direction have no descriptions). The description mentions the window but adds no format detail, and it is silent on the direction enum (up/down/both), the top_n cap of 100, and what category filtering means. It does not compensate for the coverage gap.

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 resource ("Return markets") plus the defining scope ("whose YES probability moved the most in a window"), which clearly separates it from sibling reads like market_price_history or markets_top_volume. It does not, however, name any sibling or explicitly contrast its output with them, so it stops short of a 5.

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?

Usage is only implied: the phrase "in a window" tells the agent it needs a time range, and "moved the most" implies a comparative-ranking use case. There is no explicit when-to-use guidance, no exclusions, and no pointer to market_price_history for raw series or markets_top_volume for volume ranking.

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