Skip to main content
Glama

AstroNest — Vedic Astrology Readings

Gemstone assessment

assess_gemstone
Read-onlyIdempotent

Use this when the user asks whether they should wear a particular gemstone (blue sapphire, emerald, pukhraj, a crystal), or whether a stone they wear suits their chart. Answers the prescription, not the future: which planet the stone strengthens, what that planet owns from this ascendant, whether a classical rule (a dusthāna or kendrādhipati lordship, a māraka) argues against strengthening it, and whether the reason is permanent or lasts only as long as the running period. Returns a verdict — well_founded, period_bound, no_ground, contraindicated or unrecognised — with every ground for and against, the planet's capacity at its degree, when the chart puts the planet in scope, the stones the sources hold apart from it (checked against alsoWearing), and wearing detail (finger, metal, day, weight, with the book it comes from) only when the chart gives a reason to wear it. When the source states a caution about the stone, the response says so and names the book. A word that covers several stones ("sapphire") is answered with the candidates. Nothing here predicts what a stone does. Deterministic: no language model is called. The birth time is required. Cost: 5 credits per call (only successful calls are charged; a sandbox key is free and returns a fixed sample). Deterministic: the same input always gives the same answer. Example arguments: {"birthData":{"date":"1990-05-12","time":"14:35","timezone":"Asia/Kolkata","latitude":28.6139,"longitude":77.209},"gem":"blue sapphire","alsoWearing":["ruby"]}

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "birthData": "<birthData>",
      "gem": "<gem>"
    },
    "name": "assess_gemstone"
  }
}

Input Schema

NameRequiredDescriptionDefault
gemYesOne stone, in English or by its Indian name: "yellow sapphire", "pukhraj", "emerald", "moonstone".
birthDataYesThe person's birth data. The time is required: every period depends on the rising sign.
alsoWearingNoOptional: stones already worn. When the chart puts the planet in scope, a pairing the sources hold apart is reported as a conflict.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds substantial context beyond them: deterministic with no language model called, 5 credits charged only on success, sandbox key behavior, and the exact verdict vocabulary (well_founded, period_bound, no_ground, contraindicated, unrecognised). It also discloses conditional behavior — wearing detail appears only when the chart gives a reason, and ambiguous terms like 'sapphire' return candidates rather than a single answer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded correctly: trigger first, then what it answers, then output, then constraints. Dense but not padded; the only real waste is redundancy — 'Deterministic: no language model is called' and 'Deterministic: the same input always gives the same answer' say the same thing twice and partially restate idempotentHint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nested-object tool with an output schema, everything an agent needs is present: trigger, exclusion, the verdict enum, edge-case handling for ambiguous stone names, cost, and the hard prerequisite of birth time. Since an output schema exists, the description is not obliged to detail return shape, and the verdict summary it does give is a bonus rather than a gap-filler.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description earns an extra point by explaining semantics the schema cannot: 'a word that covers several stones ("sapphire") is answered with the candidates' clarifies how `gem` is resolved, and `alsoWearing` is described as a conflict-check against stones the sources hold apart. The birth-time requirement is restated with its consequence ('every period depends on the rising sign').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('assess whether the user should wear a particular gemstone') and sharpens the scope with an explicit negation ('Answers the prescription, not the future'). An agent can distinguish it from every sibling (get_chart, get_guidance, find_muhurta) without opening a schema, since none of them answer gemstone-prescription questions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use this when the user asks whether they should wear a particular gemstone... or whether a stone they wear suits their chart' gives a concrete trigger, and two explicit when-not clauses bound it: 'Answers the prescription, not the future' and 'Nothing here predicts what a stone does.' The remaining prerequisites (birth time required, 5 credits per successful call, free sandbox key) are all stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.