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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world call, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a cost of 20 credits (Tier 2) and the endpoint, which matters for quota-aware planning. It does not describe what the returned flag payload looks like, but an output schema exists to carry that.

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 substantive sentence is front-loaded and the bracket block packs group, endpoint, required params, and cost compactly. No filler prose. The bracketed metadata is mechanical but earns its space given it carries the cost signal.

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 15-parameter calculation endpoint, the description covers only the yoga definition plus cost and the required-field list. It never says how ayanamsa or zodiacType affect the result, whether optional params are ignored, or when to prefer the aggregate Jaimini yoga tools. Safety and return shape are handled by annotations and the output schema, but the invocation context is thin.

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?

The tool takes 15 parameters at 33% schema description coverage, and the description only repeats the four required ones (date, time, latitude, longitude). Eleven optional parameters, including ayanamsa, zodiacType, houseSystem, and the compact-mode fields/precision pair, get no treatment here, and for a Jaimini yoga computation the sidereal/ayanamsa choice is materially consequential. The description does not compensate for the coverage gap.

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 the specific technique and states the exact conditions computed: 'AK + AmK both in dusthanas (6/8/12), poverty/struggle flag.' That is a concrete verb-plus-resource statement an agent can act on, and it distinguishes this tool in substance from siblings like astroway_vedic_yogas_jaimini_dhana or _raja. It never explicitly points to those siblings, so it stops short of a 5.

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?

There is no guidance on when to choose this single-yoga tool versus astroway_vedic_jaimini_yogas or astroway_vedic_yogas_jaimini_full, nor any prerequisites beyond the echoed required parameters. 'Remedies recommended' is an output note, not usage guidance. An agent must infer the selection criteria entirely from the yoga's name.

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