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

Annotations already mark the tool as readOnlyHint=true and destructiveHint=false. The description adds complementary behavior detail: it aggregates into four windows, counts, and top events, and emphasizes it is purely a summarization operation. This aligns with the read-only hint and gives the agent confidence it has no side effects. It doesn't waste space restating the annotations.

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?

Three sentences that are dense and purposeful: the first identifies the action and windows, the second enumerates the output structure, the third provides the use case. No wasted words, and the key action and purpose are 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?

For a tool with 8 parameters, nested objects, and no output schema, the description provides a solid high-level contract: four windows each with counts, breakdowns, and top events. An agent can anticipate the shape of the result. It stops short of specifying the exact JSON structure or array ordering, but the schema and examples handle parameter details. Given no output schema, this level of responsiveness is nearly complete.

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?

Input schema covers 100% of parameters with detailed descriptions (e.g., top's max, lang fallback, compact's token savings, domains enum, birthData fields). The description itself adds no parameter semantics beyond saying windows are measured 'from the start date,' which is already documented in startDate. Since the schema carries the burden, a baseline 3 is appropriate.

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 uses a concrete verb ('Roll') with a clear resource ('cross-domain forecast for a single birth subject') and specifies the exact output: four windows with counts, per-domain and per-type breakdowns, and top events. This differentiates it from siblings like post_forecast_timeline or post_forecast_transits, which would return event lists rather than pre-summarized rollups.

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 a clear use context: 'Built for a glanceable what-is-coming strip ... without scanning the full event list.' This implies when to choose this over a timeline or raw forecast tool, though it doesn't explicitly name alternatives or give exclusion criteria. The context is strong enough to guide an agent.

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