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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description goes well beyond this by disclosing the directional verdict rule ('the bride total must be equal to or below the groom total'), the weighting scheme (Lagna 1, Moon 0.5, Venus 0.25), and the consequence that swapping the two inputs can flip the verdict. This is substantive behavioral context that an agent needs to interpret results correctly and that no annotation or schema field conveys.

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 dense and long, but every sentence earns its place: purpose, computational method, return contents, verdict interpretation, and usage context. It is front-loaded with the core action in the first sentence. The middle sentence packs a lot of technical specificity (planets, bhavas, weights) that could have been trimmed, but it is all relevant to correct invocation and interpretation, so only a small deduction for density.

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 complex domain tool with nested person objects, the description, combined with a fully documented schema and an output schema, tells the agent everything needed: what it computes, how to interpret the directional verdict, what the response includes, and when to use it relative to other compatibility checks. The sibling list shows related tools, and the description's explicit differentiation from koota-based matching prevents confusion with compatibility_dashakoot. Nothing essential 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?

The input schema has 100% description coverage, with detailed explanations for person1 (groom), person2 (bride), ayanamsa, timezone, and the rest. The tool description adds no parameter-level detail beyond what the schema already provides, which matches the baseline of 3 when the schema carries the weight. The directionality nuance is already captured in the person1/person2 property descriptions.

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 opens with a specific verb and resource: 'Calculate Papasamyam, the balance of malefic (papa) points between two birth charts, for Vedic marriage matching.' It enumerates exactly which planets, bhavas, and reference points are used, which clearly differentiates it from sibling compatibility tools like dasxxakoot or general compatibility. The sentence 'The verdict is a comparison and never a judgement on one person' further pins down the tool's unique semantic.

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 explicitly says when to use it: 'Use it beside Gun Milan and the ten porutham sheet on a matrimonial platform' and gives the rationale: 'since a koota score says nothing about malefic balance.' This is clear contextual guidance. It stops short of naming the specific sibling API (e.g., post_vedic_astrology_compatibility_dashakoot) as the Gun Milan tool or listing explicit 'do not use when' conditions, so it earns a 4 rather than a 5.

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