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

With no annotations, the description carries the full behavioral burden and does disclose important traits: history is guaranteed only for the committed universe (ETH/BTC/USDC/USDT x ethereum/arbitrum/base), and unsupported pairs silently degrade to a live point signal with no curve. It does not mention auth requirements, rate limits, or error behavior, which leaves some gaps for a read tool with no annotation support.

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?

Two sentences, front-loaded with the returned metrics before the usage framing and coverage caveat. Dense and mostly waste-free, though the metric list and the coverage/fallback clause are both packed into long clauses that could be trimmed slightly.

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?

There is no output schema, so the description correctly enumerates what comes back (verdict stability, degraded-time ratio, worst deviation, mean credibility, recent series), which is the right substitute. Combined with the coverage limitation and the oracle_watch fallback, an agent has enough to call it correctly, though error/empty-history behavior is 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 baseline is 3: days, chain, symbol and interval (including the 8-30d hourly and >30d daily rollup rules) are all documented in the schema. The description only restates the window as "last N days" and "recent series," adding no syntax or format detail beyond what the schema already carries.

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 names a specific verb (retrospective trend) and resource (Oracle Watch for an asset) and enumerates the exact outputs: verdict stability, degraded-time ratio, worst deviation, mean credibility, plus the recent series. It explicitly distinguishes itself from the live sibling (oracle_watch) by framing itself as historical judgment rather than an instantaneous health check.

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?

"Use it to judge whether a feed has been dependable, not just whether it is healthy this instant" states the when-to-use case and implicitly routes instantaneous checks to oracle_watch. It also gives an explicit coverage boundary and the fallback behavior (other pairs return a live point signal from oracle_watch but no curve), so the agent knows when this tool will not give what it expects.

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