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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety is covered. The description's real contribution is expectation-setting: windows are month-granularity approximations from chart promise, dasha and transits, not precise predictions. It does not address latency, whether results are deterministic across runs, or what a 'no window' answer looks like, which matters for a divination-style tool.

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 dense sentences front-load the what, the method, and the output granularity, then a short 'Use for' clause with example utterances. Every element earns its place; the methodology run-down is slightly long but justified because it explains why results are windows rather than dates.

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, 9 parameters and an open-ended astrology domain, the description does its job: it explains inputs' role (birth chart), method, and the shape of the answer (month windows). A closer to 5 would require saying how many windows are typically returned or how topic and years shape the response, but nothing essential for a correct call is missing.

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%, so every parameter is already documented, and the baseline of 3 applies. The description reinforces the topic enumeration and the 'one life area' constraint plus month-level granularity, but adds no syntax, default, or trade-off detail (e.g. how years interacts with window sizing) 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 names a specific verb ('finds the good time windows'), a scoped resource (one life area: marriage, career, wealth, children, property, education, health) and a concrete output granularity ('windows (months), not exact dates'). The methodology clause ('chart's promise for that house, Vimshottari dasha periods, Jupiter–Saturn transits') separates it from a generic dasha_timeline or get_kundli call without the agent needing to open schemas.

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?

Usage is grounded in real trigger phrases ('when will I get married', 'when will I get a job', 'shaadi kab hogi'), so the agent can pattern-match user intent to this tool directly. It also states the one-topic constraint, implicitly telling the agent not to bundle multiple life areas into one call. It stops short of explicit when-not conditions or naming an alternative tool for other timing questions.

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