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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them: it discloses the ranking metric and unit (24-hour change in points), the cap of 20 results and at most two outcomes per event, the coverage universe (300 most-traded markets with ≥$10K 24-hour volume), and exclusion thresholds (markets at ≤1% or ≥99%, individual sports/esports games, mature topics, uncategorized Up-or-Down and tweet-count markets). These constraints materially change what an agent should expect to see and cannot be derived from the structured fields.

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 activation condition and example queries, then moves to return shape, then to inclusion/exclusion rules — a sensible order. The exclusion clauses (sports games vs futures, mature topics, Up/Down and tweet-count markets) are individually informative but accumulate into a dense block, and the "not advice" and "do not use this to choose a market" sentences partly overlap.

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?

Given an output schema exists (so return values need no explanation) and annotations cover the safety profile, the description still supplies everything an agent needs to call and interpret it correctly: what is ranked, the unit of change, the result cap, the deduplication rule, and the universe/exclusion boundaries. No material gap remains for a read-only, three-optional-parameter listing tool.

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 limit, category and direction are already self-documenting, and the description only restates them collectively as "Optional filters: direction and category." It adds no extra syntax, interaction, or default behavior beyond what the schema and enums already convey, so the baseline 3 applies.

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 — returns Polymarket markets ranked by 24-hour change in market-implied probability — and the example user questions ("biggest movers", "what odds are dropping in crypto") pin down the intent precisely. It never names its closest sibling get_trending_markets, so the agent must infer the trending-vs-movers boundary from the ranking metric alone, which keeps it 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?

The opening "Use this when the user asks..." clause plus four concrete example utterances give clear activation conditions, and the closing lines explicitly exclude using it to pick a market or trader to invest in. However, the exclusions are about financial advice, not about routing to alternatives — no sibling tool (get_trending_markets, get_market_flow, get_price_history) is named for cases this tool does not cover.

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