Kundli (one call)

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds real behavioral detail beyond that: 'targetDate (default now)' defines the temporal snapshot for the dasha, and the `present` list tells the agent doshas/yogas are reported as a found-set rather than a boolean blob. Cost (50 credits, Tier 3) is disclosed in context but not in the description itself.

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, front-loaded with the outcome ('A kundli card in one call') before the inventory of parts, and the required-parameter caveat closes it. The middle clause is dense with domain jargon and route paths, but every element maps to actual output content, so nothing is padding.

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, the description needn't explain return shapes and correctly focuses on composition, defaults, and required inputs. It is slightly incomplete on the target time fields (targetTime, targetTzOffset are never mentioned) and does not flag that the composite costs 3x a single sub-route, but for a wrapper tool of this complexity it is substantially 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?

Schema description coverage is 100%, so the baseline is 3; the description earns an extra point by surfacing the calling constraints an agent most often trips on: latitude and longitude are required, `time` accepts `HH:mm:ss` or `HH:mm`, and `targetDate` defaults to now — a default the schema does not state. It does not discuss ayanamsa/zodiacType/houseSystem interplay, but the schema already does.

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 deliverable (a kundli card from one call) and enumerates its exact contents: D1 lagna, nine grahas, Moon nakshatra/pada, running Vimshottari maha/antar, and Parashari yogas/doshas. It also names the four sibling routes (/vedic/varga/D1, /vedic/dashas/vimshottari/antar, /vedic/yogas/parashara/full, /vedic/doshas/parashara/full) whose answers this aggregates, so an agent can distinguish it from those tools without opening 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?

The 'one call' framing plus the explicit equivalence to four separate routes makes the selection rule clear: use this instead of chasing the individual endpoints when you want the combined card. There is no explicit 'do not use when…' clause (e.g., versus astroway_reports_vedic_kundli, which produces a report), so it falls short of a full 5.

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