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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-redundant behavior: the call is synchronous, and it is metered at 50 credits for the first candidate plus 20 for each further one, reported via X-Credits-Used — critical for an agent deciding how many candidates to submit. It does not mention rate limits, failure modes, or behavior when a candidate's chart is invalid.

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 core sentence is front-loaded with the operation, scope, ranking and return summary, and the bracketed metadata (Group, Endpoint, Required, Cost) is scannable. The first sentence is long and packs ranked-output detail that partially duplicates the output schema, but nothing is wasted outright.

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 a rich output schema, an agent needs purpose, cost and constraints, and the description supplies purpose, sync behavior and the full billing formula. Remaining gaps — how many candidates are worth submitting under the credit curve, and how this relates to the single-pair compatibility tools — are minor given the schema and annotation coverage.

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 89%, so the schema already carries the semantics of school, sortBy, mangalSchool, minAshtakoot, fields and precision. The description only echoes two of those (profileRole and sortBy) and adds no syntax, defaults or edge-case guidance beyond what the schema states, so the baseline of 3 applies.

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?

States a concrete operation: one profile matched against up to 100 candidates, ranked by Ashtakoot points or Porutham when sortBy is set, returning top kootas, Porutham count, Mangal verdict and uncancelled doshas. The 'bulk / up to 100' framing inherently distinguishes it from the single-pair siblings such as astroway_vedic_compatibility_ashtakoot and astroway_vedic_compatibility_porutham.

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 scenario is implied by 'one profile against up to 100 candidates' and the sortBy reference to Porutham, but the description never names an alternative tool or states when to prefer a single-pair counterpart (ashtakoot, porutham, full) over this bulk call. A reader can infer the screening use case but must guess at the boundary conditions.

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