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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and side-effect questions are covered structurally. The description adds real value beyond that by disclosing the computation's provenance (VedicDost software) and the full scope of what is produced, including classical cancellation (parihar) and the dual Manglik check. It says nothing about failure modes (e.g. missing birth time) or response shape, which keeps it below a 5.

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?

The definition is front-loaded: the calculation and its scope come first, and the trigger phrasings come last. The parenthetical enumeration of all 8 kootas is dense but earns its place by telling the agent exactly what the result contains in the absence of an output schema. Minor length overhead from the full koota list, but nothing is redundant.

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, the description carries the burden of describing the return contents, and it does so by enumerating the 8 kootas, the out-of-36 total, dosha plus parihar, and the Manglik result. Input requirements are fully specified by the schema. It would be stronger with a note on the time-omission limitation at the top level, but the schema already covers that per-field.

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 nested field (date, time, place, latitude/longitude, timezone) is already documented, including the consequence of omitting time. The description adds only the framing that both people's birth details are required inputs, which the schema already enforces via the required boy/girl objects. Baseline 3 is appropriate when the schema does the heavy lifting.

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 calculation (Ashtakoot guna milan out of 36) for a specific pair of subjects (two people, from birth details) and enumerates the exact constituents returned: all 8 kootas by name, Nadi/Bhakoot dosha with parihar, and a Manglik check for both. This clearly separates it from the single-person sibling get_kundli, which cannot do a two-person comparison.

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?

It gives three concrete user phrasings ("kundli milan", "guna milan", "are we compatible for marriage") that map directly onto when to call it, which is strong positive routing. It stops short of stating when-not to use it or naming an alternative (e.g. check_dosha for a single-person dosha query), so it is clear context without explicit exclusions.

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