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

Annotations already declare readOnly, idempotent and non-destructive, so the description earns credit for adding what they cannot: a 50-credit Tier 3 cost, the POST /v1/vedic/compatibility/navamsa endpoint, and the explicit warning that no score is returned. That last point prevents a real misuse, since an agent might otherwise wait for a numeric match value.

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 output contents are front-loaded in one dense sentence, followed by the no-score caveat, and the bracketed metadata block is scannable. Every element carries information, with only mild redundancy in repeating the required parameters.

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?

Given an output schema exists, the description need not explain return values, and it covers the remaining agent-facing gaps: cost tier, endpoint, required inputs, and the absence of a score. What remains, such as when to pick this over the many compatibility siblings, is a usage-routing gap rather than a completeness one.

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 description only restates that chart1 and chart2 are required, which the schema already enforces, and adds no meaning for fields or precision. The schema itself is rich here, documenting the birth-data fields, the groom/bride role of chart1/chart2, and compact-mode behaviour, so the baseline 3 for a half-covered but well-documented schema is appropriate.

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 resource and its contents: each partner's D9 Lagna, Moon, Venus and 7th house with lords and vargottama flags, plus the relation of the two Moons' navamsa lords. That distinguishes it from the single-chart sibling astroway_vedic_varga_d9, though it never names a sibling explicitly.

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?

Usage is only implied through the word 'compatibility' and the reference to cancelling Nadi dosha, which hints at a link to dosha_cancellation without stating when to prefer this over compatibility_full, ashtakoot, or dashakoota. The 'No score' warning usefully tells the agent not to expect a verdict here, but no exclusions or alternatives are given.

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