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

Annotations are all false, providing no safety hints, so the description carries the burden. It discloses meaningful side effects: "Reserves AI credits up front" and dispatches a multi-stage pipeline. It also clearly describes the asynchronous behavior and what determines the return path. This exceeds what the annotations or schema convey, offering high transparency.

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?

Two sentences, both dense and purposeful. The first identifies the action, the second details behavior and outcomes. No filler or repetition; the structure front-loads the core purpose. This is exemplary conciseness.

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?

The tool is complex (cost, async, pipeline), yet the description covers purpose, cost side-effect, pipeline components, and the two return paths. An output schema exists, so return values need not be explained. Missing are prerequisites (e.g., forecast must exist) and potential error conditions, but these are not critical given the description's breadth. Overall, it is largely complete for an execution 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?

Schema description coverage is 50%: wait_seconds has a description, forecast_id does not. The description adds context about wait_seconds by linking it to the inline-vs-poll outcome, but it doesn't elaborate on forecast_id beyond what the name and format imply. Since coverage is not low, a baseline of 3 is appropriate, and the description adds moderate value without fully compensating for the undocumented forecast_id.

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 with a specific verb and resource: "Run a forecast now." It distinguishes from siblings by naming the dispatched pipeline (backtest + projection + correlation) and the two return modes (inline result vs. pollable run_id). This makes it clear that run_forecast initiates a run, unlike create_forecast or get_forecast_run.

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 concrete usage guidance: it explains how wait_seconds controls whether you get the result inline or a poll handle, and explicitly references get_forecast_run for polling. However, it does not explicitly state prerequisites (e.g., the forecast must already exist) or when not to use this tool in favor of alternatives like run_analysis, so it stops short of full when/when-not guidance.

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