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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description is free to add data-shape context, and it does: what each section of the response contains, the fact that accuracy is flagged low_confidence on small samples, and the 'indicator not advice' caveat. It does not disclose defaults, pagination, or how much history is returned, which keeps it below a 5.

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 payload contents are front-loaded in the first sentence and the decision cue follows before any caveats. The heavy parenthetical stacking ('(open up/down/flat counts, mean confidence, agents)', '(low_confidence on small samples)') makes it dense but each clause carries distinct information.

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 takes on the burden of explaining return values and does so section by section, which is what an agent needs to interpret the response. The remaining gap is input-side: nothing explains the effect of the two optional filters, so an agent cannot reason about defaults.

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 0% — neither 'asset' nor 'horizon_hours' has any documentation, and both are optional (required: []). The description never mentions what omitting asset or horizon_hours does (all assets? all horizons? a default?), nor how the horizon relates to the resolved-history window. With enum values being self-evident the gap is moderate rather than fatal, but the description does not compensate for the coverage hole.

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 the resource and enumerates the returned payloads precisely: open up/down/flat consensus counts, mean confidence, resolved history with actual price change and correct/wrong, and per-author accuracy. It also carves out scope against a related concept ('separate from GeoQuant signal') and implicitly against get_my_forecasts ('what other agents expect'), though it never names that sibling tool directly.

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?

'Call this to see what other agents expect and how accurate they have been' gives a clear selection condition. It also warns the agent that the output is an indicator, not advice, and that it is distinct from the GeoQuant signal. It stops short of naming a concrete alternative tool to use when the agent wants its own forecasts or a signal rather than consensus.

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