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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, but the description adds materially beyond them: credit cost and billing behavior (3 credits, only successful calls charged, free sandbox key), determinism ('same input always gives the same answer'), no-model epistemics, and, importantly, that caste/prenatal-sex/death-timing rules are withheld and counted, and that no KP judgment is asserted.

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?

Front-loaded with the usage trigger, then organized into one block per mode, so it scans well. It is long, however, and spends considerable space narrating output contents (lagna lord, Moon, Tājika contacts, verdict vocabulary) that the existing output schema could carry, which dilutes conciseness somewhat.

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 complex 8-parameter tool with nested objects, one required field, and an output schema, the description covers the remaining gaps an agent needs: the mode-selection logic, the credit/auth model, the withholding policy, the determinism guarantee, and a full worked example. Nothing material for correct invocation is left unstated.

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 the schema already carries most parameter meaning and the baseline is 3. The description still adds value by stressing that `place` is required and 'never defaulted' (a wrong longitude is a different chart), tying `birthData` to the deal mode rather than blending it, and explaining what `deal` and `horaryNumber` each cause the tool to compute.

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+resource (casting the praśna chart of the moment and place) and explicitly distinguishes itself from natal-chart siblings: 'answered from the moment of asking rather than from a birth chart'. It also enumerates the three distinct modes (plain question, deal praśna, KP horary number), so an agent can tell exactly what it returns versus get_chart or get_venture_timing.

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?

Opens with an explicit trigger condition ('when the user asks a specific question and wants it answered from the moment of asking') and gives the alternative it is not. It then states the selection conditions for each mode: use `deal` for a commercial question, `horaryNumber` 1–249 for a KP astrologer's number, and `birthData` only alongside `deal`. When/when-not/alternatives are all present.

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