Get ML outperformance prediction

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

The description goes well beyond the readOnlyHint and openWorldHint annotations. It discloses the structure of the return value (data.prediction fields), the meaning of the isHeuristic fallback, and the early-day refresh limitation. These are non-obvious behavioral traits that an agent needs to correctly interpret results, making the description transparent and useful.

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 dense but logically organized, starting with purpose, then return fields, then alternative tool, then caveats. Every sentence carries useful information, but the long first sentence with semicolon-separated fields could be broken up for easier parsing. Despite this, there is no fluff or redundancy, earning a strong score.

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 full responsibility for describing the return structure, which it does thoroughly. It also covers the heuristic fallback and timing edge case, making the tool's behavior predictable in both normal and exceptional conditions. The description is complete enough for an agent to invoke the tool, interpret results, and know when to consult a sibling 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 input schema already documents horizon with an enum and description, covering 50% of parameters. The description adds little beyond the schema: it repeats that horizon is in trading days and does not clarify ticker's format or constraints. Since the coverage is exactly 50%, a baseline score of 3 is appropriate without substantial added parameter clarification.

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 clearly states the tool's function: it returns the ML model's probability that the ticker will outperform the S&P 500 over a horizon. It also explicitly distinguishes itself from a buy/hold/sell call and from the sibling tool stoquant_explain_ml_prediction, which covers the feature-level 'why'. This level of specificity and differentiation makes the purpose highly clear.

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?

The description provides explicit usage guidance: it directly names stoquant_explain_ml_prediction as the alternative for feature-level explanations, and warns that the prediction is not a buy/hold/sell signal. It also includes a timing caveat about early trading day data freshness, telling agents to treat null predictions as 'not yet computed' rather than errors. These are concrete when-to-use and when-not-to-use instructions.

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