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

Annotations already carry readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds substantial behavioral context on top: Rajju and Vedha act as 'explicit hard vetoes that disqualify a match whatever the rest of the sheet reads', and five of the ten poruthams are direction-sensitive counting from bride to groom. These are non-obvious behaviors an agent must know to interpret results correctly, and they go well beyond what the annotations state.

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?

Roughly three dense sentences, each earning its place: the calculation and return shape, the sibling-system distinction with use context, and the direction warning. It is front-loaded with the verb and resource, and lists the ten poruthams compactly. Slightly long, but the complexity (ten named components, veto rules, Ayanamsa context) justifies the length; no filler or tautology.

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 (returns covered), 100% schema coverage on 6 parameters including nested objects, and annotations covering the safety profile, the description is nearly complete. It supplies the essential missing context: the system identity, the sibling distinction, the veto semantics, and the groom/bride ordering constraint. It could add failure or boundary behavior, but nothing an agent needs to invoke this correctly is absent.

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 coverage is 100%, so the schema already documents every parameter thoroughly, including person1=GROOM and person2=BRIDE. The description adds value by explaining WHY the direction is load-bearing ('five of the ten poruthams count from the bride birth star to the groom birth star'), reinforcing the role semantics beyond what parameter names alone convey. This is a meaningful increment over the schema baseline of 3.

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 the South Indian ten porutham marriage match (Dashakoot...)'. It enumerates all ten poruthams, states the return shape (pass/fail each, total out of ten, vetoes), and explicitly disambiguates itself from the sibling 'POST /vedic-astrology/compatibility' 36-point Ashtakoot system. An agent can tell exactly what this tool computes and how it differs from its nearest sibling without opening either schema.

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 names the alternative ('the 36 point Ashtakoot Gun Milan on POST /vedic-astrology/compatibility'), states that the two are never reconciled, and gives a concrete audience ('a Tamil, Malayalam or Telugu matrimonial desk can read the sheet it actually uses'). It also warns that direction matters and person1/person2 are not interchangeable. The when-to-use is clear, though the when-not-to-use is conveyed by contrast rather than an explicit routing instruction.

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