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

With no annotations, the description carries the full burden and does well: it discloses the committed-universe coverage guarantee (ETH/BTC/USDC/USDT x ethereum/arbitrum/base) and the degraded fallback behavior for other pairs. It omits operational traits such as auth requirements, rate limits, or whether the window is capped by data retention.

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 core purpose and metric list, then the usage rule, then the coverage caveat. Every sentence earns its place; the metric enumeration is a little dense but functional.

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?

No output schema exists, so the description must describe returns, and it does so concretely (verdict stability, degraded-time ratio, worst deviation, mean credibility, series). The fallback return is also covered. Minor gap: the length/granularity of the 'recent series' and any retention cap are unstated.

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 the schema already documents days, chain, and interval (including the roll-up rules), giving a baseline of 3. The description only gestures at 'the last N days' and adds no meaning beyond the schema.

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?

Names a specific verb+resource (retrospective oracle watch trend for an asset) and enumerates the exact outputs: verdict stability, degraded-time ratio, worst deviation, mean credibility, recent series. It is clearly distinguishable from the sibling oracle_watch, which the description implicitly positions as the live/instant counterpart.

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?

Explicitly states the usage condition ('judge whether a feed has been dependable, not just whether it is healthy this instant'), which routes the agent away from instantaneous tools like get_feed_health/oracle_watch. It also gives an explicit when-not: non-committed pairs return only a live point signal with no curve.

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