forecast_tft

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

No annotations are provided, so the description carries the full burden. It discloses that quantiles are raw and not isotonic-calibrated, but fails to mention important behavioral constraints such as whether the tool only works for the 21 watched countries it was trained on, or any authentication, rate limits, or idempotency details.

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 two sentences with no wasted words. The core purpose and model type are front-loaded, followed by an important caveat. Every sentence adds value.

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?

Despite the tool's complexity (deep learning model with quantile bands) and no output schema, the description does not explain the response structure beyond mentioning 'honest_caveats'. It also omits that the tool likely only works for the 21 watched countries, leaving a significant gap for agent understanding.

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% for the single parameter (country_code), which already describes its format. The description adds that the model was trained on 21 watched countries, hinting at potential input restrictions but not explicitly defining valid values. This does not significantly enhance understanding beyond the schema.

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 it provides a 'shutdown-risk forecast for a country' using a 'Temporal Fusion Transformer' model with quantile bands, which specifies the verb and resource. However, it does not explicitly differentiate from sibling forecast tools (e.g., forecast_hourly, forecast_multi_horizon) beyond mentioning the model type.

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 includes a caveat about raw quantiles and to check 'honest_caveats', but provides no guidance on when to use this tool versus alternatives like forecast_7day_shap or forecast_platform. No explicit when/why/alternatives.

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