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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false) but do not explain what the tool computes or returns. The description adds real behavioral context: server-time chart casting, a fitness check preceding judgment, a named output structure (timingWindows, judgmentDimensions.timing), the condition under which no date appears, and an anti-hallucination guardrail ('Never supply dates that timingWindows does not contain'). It does not explain the outcome-confirmation hook's mechanism or any persistence, but it goes well beyond 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?

A single dense, front-loaded paragraph that leads with the action and then layers the seedNumber/timing conditional and the guardrail. Nearly every clause earns its place, though the middle conditional sentence is convoluted enough to require a second read.

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 an output schema present, return values needn't be enumerated, yet the description usefully names the two fields an agent will consult and explains their conditional emptiness. For an 11-parameter, non-read-only tool this is nearly complete; the main omissions are how the location inputs interact with 'server-time' casting and what the outcome-confirmation hook concretely does.

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?

At 55% schema coverage across 11 parameters, the description must carry real weight, and it does for the most consequential ones: seedNumber is framed as the querent's own pick from 1 to 249 that unlocks KP Reader VI dated windows, and its absence is tied to a specific output field's explanation. It also anchors the career category. However, location inputs (place/latitude/longitude/timezone) and tradition/referenceHouse receive no descriptive treatment, leaving a gap the schema only partly fills.

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?

States a specific verb and resource chain: 'casts a server-time horary chart, checks chart fitness, and returns an auditable structural judgment plus outcome-confirmation hook.' This is distinctly a horary/Prashna question tool, separating it from the many analyze_* natal-chart siblings. An agent can identify the operation and its scope without opening the schema.

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?

Gives concrete conditions of use: for 'when will I be promoted / get a job' under category career, pass seedNumber to obtain dated windows; without it, or when the chart is unfit or timing is not promised, no date is returned. It also excludes a case ('Job-change questions are not timed'). It stops short of naming sibling alternatives such as calculate_kp or record_prashna_outcome, so routing is inferred rather than explicit.

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