getPredictionPriceHistory

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: a stricter 2 req/s rate limit, no caching, two distinct query modes, interval semantics, and fidelity's auto behavior. It stops short of describing response field details or behavior when both/neither mode parameter is supplied.

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 well structured and front-loaded: a clear purpose sentence, returns statement, numbered modes, parameter definitions, a rate-limit note, and an agent hint. Every sentence adds actionable information; nothing is redundant or filler.

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?

The description is highly complete for a read-only query tool: it covers modes, parameters, rate limits, and alternative routing. The main gap is that it doesn't explicitly state whether exactly one of tokenIds or eventId is required, and since there is no output schema, it gives only a high-level 'price time series for chart display' rather than response structure details.

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?

With 0% schema description coverage, the description carries the full semantic burden and does so well. It explains interval as a time-range control with all enum values listed, fidelity as minutes between data points with 0 meaning auto, tokenIds as supporting up to 20 token IDs, and eventId as a way to get history for all tokens in an event.

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 a specific verb and resource: 'Query historical price data for prediction outcome tokens.' It clearly distinguishes this from current-price tools by explicitly stating 'Do NOT use this for current prices — use getPredictionTokenPrice instead.' The purpose is unambiguous and differentiates from sibling prediction tools.

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 gives explicit when-to-use guidance: historical price chart history for specific tokens or events, with interval recommendations for daily vs weekly views. It also names the alternative getPredictionTokenPrice and explicitly excludes current price queries. Mode selection between tokenIds and eventId is clearly explained.

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