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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial context beyond them: fills at >=99¢ or <=1¢ are excluded, individual sports and esports games are excluded, each fill is counted once, and dollars equal shares times price. It also preempts misuse with 'a large trade is not a forecast, and these tools cannot place trades.'

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 use case and examples, which is the right ordering. It is a single dense paragraph that repeats defaults already present in the schema (limit 15, hours 24), which costs some tightness but nothing is genuinely off-topic.

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 filtered read tool with an output schema, all decision-relevant information is present: trigger conditions, exclusions, dedup and dollar accounting, filter formats, and the read-only guarantee. The return fields are described as well, so the agent can predict the response shape even without opening the output schema.

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 100% and each parameter is documented, so the baseline is 3. The description goes slightly beyond by restating defaults and ranges in context (min size $1K–$1M default $10K, window 1–168 hours default 24) and by explaining that the market filter accepts slugs, supported links, condition ids, or plain words.

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 ('Scans Polymarket.com's public trade feed and returns... largest fills') and scopes it with a minimum-size threshold. The four quoted example queries make the target intent unmistakable and separate it from siblings like get_leaderboard and get_market_flow.

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?

Opens with an explicit 'Use this when the user asks about large or notable recent trades' trigger and gives concrete phrasings that should route here. It also names the inverse condition ('name a market to see its trades') that overrides the default exclusion of sports/esports and mature topics, so the agent knows how to escape the filter.

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