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

Annotations already mark readOnlyHint=true, and the description adds meaningful context: it uses k-NN over specific market-state inputs, returns median/quartiles/hit-rate per analog and in aggregate, and explicitly says it is not a prediction. It also notes the k range and default, plus episode-separation and REST equivalence, going well beyond annotation-only disclosure.

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 with a [CONTEXT] prefix, followed by concise but complete details on methodology, input space, output statistics, k range, and caveats. Every sentence contributes value, and it is appropriately front-loaded.

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 carries the full burden of explaining return values. It enumerates the input state variables, forecast horizons, statistical summaries, aggregation method, and the non-predictive caveat, making it fully informative for a k-NN analog tool.

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?

The schema only provides a default of 12 with no description. The tool description adds crucial semantics: k is the number of nearest neighbors, valid range 3-25, and default 12, making the parameter's purpose and acceptable inputs fully clear.

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 states the tool retrieves nearest historical market-state analogs via k-NN and summarizes actual subsequent SPX/NDX/BTC returns over 1d/5d. It specifies the resource (cross-asset state) and output aggregates, distinguishing it from sibling tools focused on signals or indicators. The 'Conditioning context, NOT a prediction' phrase further clarifies its role.

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?

It clearly indicates this is for conditioning context rather than prediction, and is explicitly tied to 'right now.' However, it does not explicitly name alternative tools or state when not to use it, though the distinction from signal-based siblings is implied.

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