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

No annotations are provided, so the description carries the full burden, and it does disclose meaningful behavior: the signal is continuous rather than a point-in-time read, it aggregates five named components, and it maps to a three-level verdict plus a three-value action recommendation — effectively the return semantics in prose. It does not state refresh cadence, cost/latency, or failure modes for a 'ongoing' signal, so it falls short of full disclosure for a monitoring tool.

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?

Three sentences, zero filler: the purpose and verdict semantics come first, the gating guidance second, and the sibling pairing last. Each sentence earns its place.

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?

With no output schema, the description must convey return shape, and it largely does via the verdict levels and named components. The gap is operational: the optional chain parameter's default/aggregation behavior and the signal's refresh cadence are undefined, which matters for an ongoing watch signal.

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% (symbol documented as an asset symbol, chain as an optional blockchain filter), so the schema already does the heavy lifting and the baseline is 3. The description adds no syntax, format, or defaults — notably it never explains what omitting chain means (cross-chain aggregation vs. default chain).

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 resource and scope: an ongoing cross-oracle risk signal for an asset, condensed into a NORMAL/CAUTION/DANGER verdict with a proceed/halt recommendation. It names its measurable inputs (consensus deviation, agreement, quorum, outliers, staleness), which cleanly separates it from one-shot siblings like get_oracle_health or compare_oracle_deviation.

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 says when to use it (gate long-running strategies: yield, keeper, portfolio) and draws a boundary against a nearby use case ('not just one-off trades'). It also names the complementary tool and the moment to pair it, pre_trade_safety_check for the decision moment.

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