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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered and the bar is lowered. The description adds real operational context beyond annotations: 'Data only — no interpretation is added' discloses the output policy, and domain semantics like 'mars_dosha>0 means Manglik' plus the default 'both systems' behavior tell the agent what to expect from the payload.

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 description is long but each section earns its place: purpose, sibling differentiation, parameter shape, then a complete return-structure map that compensates for the missing output schema. It is well front-loaded, though the full enumeration of the eight kootas and four poruthams could be condensed without losing essential guidance.

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?

This is a high-complexity tool — two required nested objects, an enum parameter, and a six-part composite return — with no output schema. The description documents every return section ('summary', 'north_indian', 'south_indian', 'boy'/'girl', dosha data, 'beeja_rasi'/'kshetra_rasi'), the default, and enum options, so an agent can invoke it correctly without schema spelunking. Nothing necessary 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 coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by linking the 'system' parameter to the shape of the returned payload and by framing the two structurally identical nested objects as boy vs. girl (groom vs. bride), which clarifies the schema's terse 'birth details' labels. The prose mirrors format examples from the schema rather than contradicting or expanding them.

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 opening sentence states the exact function — 'Check Vedic marriage compatibility between a couple' — with a specific verb and resource. The phrase 'Unlike the other tools, this needs TWO births' explicitly differentiates it from the 31 sibling get_* tools, which all operate on a single birth. The title 'Marriage Compatibility (Guṇa Milan)' adds a searchable alias for further disambiguation.

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 description provides clear selection context: it names the unique prerequisite (two birth records) and gives explicit guidance for the 'system' parameter ('By default both systems are returned; set system to north or south to get just one'). It does not, however, name concrete alternatives or state when not to use this tool — e.g., pointing single-birth Manglik checks toward a sibling like get_doshas.

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