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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description adds real operational context: cost (50 credits, Tier 3), endpoint, and the required chart pair. It also makes the scoring deterministic and auditable (specific nakshatra counts and 13 obstructing pairs), which helps an agent reason about the result rather than treat it as a black box.

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 purpose and the additive scoring relationship are front-loaded in the first clause, followed by the two rule definitions and a compact metadata block. It is dense but every line carries information; no filler or repetition.

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 two-chart calculation with rich annotations and an output schema, coverage is mostly adequate. The notable gap is chart ordering: Mahendra counting is directional (counted from one nakshatra to the other), yet the description never says whether chart1 is the reference and how that affects the 2-point award, nor how to read the 39-point total.

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% and the nested chart object is documented in unusual depth (timezone handling, field-name rejections, house-system letters), so the schema carries parameter semantics. The description only restates that chart1 and chart2 are required and adds nothing about parameter meaning itself.

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 domain resource and computation: an extended matchmaking score that adds Mahendra (2) and Vedha (1) to the Ashtakoot 36 for a 39-point maximum. That implicitly separates it from astroway_vedic_compatibility_ashtakoot, though it never names the sibling or the fuller compatibility_full variant directly.

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: by framing itself as 'extended ... on top of Ashtakoot 36', it signals when an agent would prefer it over the plain Ashtakoot tool. There is no explicit when-to-use/when-not statement, no mention of compatibility_full, and no prerequisite or alternative routing.

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