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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description goes further by explicitly stating 'Read-only public research data. No account access, no order placement or fund transfers.' It also discloses data freshness (hourly UNIQUE part_hour+venue+venue_event_id), collapse on venue_event_id, and the unsupported_filter nuance for coin-only, all of which add behavioral context beyond annotations. No contradictions present.

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?

The description is dense but well-organized, front-loading the core action and data source, then systematically covering filters, sort behaviors, and special cases. Each clause adds necessary context, though the long single paragraph could be slightly more scannable with bullet points. Still, no sentence is wasted and the structure is logical.

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 tool with 9 optional parameters, no required fields, and an output schema, the description covers every parameter's behavior, edge cases (coin-only unsupported, category empty exclusion), and related tool pointers. It also states account access limitations and non-investment-advice disclaimer, making it complete for an agent to invoke correctly without additional lookups.

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%, but the description adds significant semantic value: it clarifies that coin expands text recall only and cannot be used alone, defines allowed venue values (polymarket, predict_fun), explains sort semantics (volume_delta_today has no volume_delta column), and specifies how category matches two fields while excluding empty event_category_primary. These details go well beyond what the schema states.

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 opens with '[Read] Search prediction events on opensearch.predictionEventSignalIndex', clearly specifying the verb, resource, and data source. It distinguishes this tool from sibling news-feed search tools by focusing on prediction events, and it names the sibling endpoints for detail and orderbook ('Detail -> get_event_signal; orderbook -> get_market_orderbook'), making the scope unambiguous.

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 description provides explicit usage constraints: all query/coin/category are optional, but coin-only is an unsupported_filter. It also explains mapping nuances for sort keys (e.g., recently_listed uses create_time instead of a dedicated column, volume_delta_today maps to total_volume_usd_24h). It offers clear routing alternatives for related needs, giving an agent full context on when to use this tool versus others.

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