Astro Agents - verifiable planetary timing data and astrology

Token synastry (two launch skies compared)

token_synastry

Read-onlyIdempotent

Crypto token synastry (compatibility by sky geometry of two tokens, data only): the cross-aspects between two launch skies with orbs, harmonious / tense counts, the tightest aspects and a geometry score defined in the response, plus a shareable SVG card. E.g. {token_a: {launch_datetime: '2018-08-03T19:28:24Z', symbol: 'USDC'}, token_b: {launch_datetime: '2020-09-14T18:11:26Z', symbol: 'UNI'}}. Two launch moments (UTC block times) compared like a synastry, without houses: every major cross-aspect between token A's and token B's planets with its orb and exactness, harmonious (trine, sextile) / tense (square, opposition) / conjunction counts, the five tightest aspects as readable labels, and geometry_score = 100 x H / (H + T) where H and T sum the exactness (1 - orb / orb allowed) of harmonious and tense aspects -- an aggregate of geometry, defined in the response, not a rating. Next to it, 'substance' says how much geometry the score stands on: aspects_total, counts (harmonious, tense, conjunction), tight_aspects (orb <= 1 deg), the tightest aspect with its orb, the orb threshold, the summed exactness and a confidence label by tight aspects (rich >= 7, moderate 3-6, thin <= 2; the rule is in the response). Rows ready for pandas; result.card.svg is a server-rendered card naming both tokens, with the substance under the score. Data only — never a signal or forecast. Deterministic (JPL DE440, no LLM); every result carries meta.result_sha256. Price $0.25 per call via REST POST https://astro-agent.dev/v1/finance/token-synastry (x402 or MPP); always paid, never a free call.

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": {
      "token_a": "<token_a>",
      "token_b": "<token_b>"
    },
    "name": "token_synastry"
  }
}

Input Schema

Name	Required	Description
`card`	No	Include the shareable SVG card (result.card.svg).
`options`	No	Optional zodiac and aspect settings.
`token_a`	Yes	A token: its launch_datetime (string or unix seconds), or {launch_datetime, chain?, address?, symbol?, name?}.
`token_b`	Yes	A token: its launch_datetime (string or unix seconds), or {launch_datetime, chain?, address?, symbol?, name?}.

Output Schema

Name	Required	Description
`meta`	No	Provenance of the result.
`error`	No	x402 offer only: why payment is required.
`result`	No	The calculation result.
`accepts`	No	x402 offer only: the payment options (scheme, network, amount, asset, payTo, ...).
`endpoint`	No	The REST route that computed it, e.g. 'western/natal'.
`resource`	No	x402 offer only: the resource being paid for.
`extensions`	No	x402 offer only: protocol extensions (bazaar).
`x402Version`	No	x402 offer only: protocol version (2).

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedNov 3, 2026

addedOutput schema / anyOf

Added value: +[
+  {
+    "required": [
+      "endpoint",
+      "result",
+      "meta"
+    ]
+  },
+  {
+    "required": [
+      "x402Version",
+      "accepts"
+    ]
+  }
+]

addedOutput schema / properties / accepts

Added value: +{
+  "description": "x402 offer only: the payment options (scheme, network, amount, asset, payTo, ...).",
+  "items": {
+    "type": "object"
+  },
+  "minItems": 1,
+  "type": "array"
+}

addedOutput schema / properties / error

Added value: +{
+  "description": "x402 offer only: why payment is required.",
+  "type": "string"
+}

addedOutput schema / properties / extensions

Added value: +{
+  "description": "x402 offer only: protocol extensions (bazaar).",
+  "type": "object"
+}

addedOutput schema / properties / resource

Added value: +{
+  "description": "x402 offer only: the resource being paid for.",
+  "type": "object"
+}

addedOutput schema / properties / x402Version

Added value: +{
+  "description": "x402 offer only: protocol version (2).",
+  "type": "integer"
+}

removedOutput schema / required

Removed value: -[
-  "endpoint",
-  "result",
-  "meta"
-]

Changed1 schema field changedOct 31, 2026

changedOutput schema / properties / result / properties / substance / description

Previous value: -"What the score stands on: aspects_total, counts (harmonious, tense, conjunction, minor), tightest {label, orb_deg}, orb_allowed_deg, weighted_strength and confidence (rich, moderate, thin) with its rule in confidence_rule."New value: +"What the score stands on: aspects_total, tight_aspects (orb <= tight_orb_deg, 1 deg), counts (harmonious, tense, conjunction, minor), tightest {label, orb_deg}, orb_allowed_deg, weighted_strength and confidence (rich, moderate, thin, by tight aspects) with its rule in confidence_rule."

Changed2 schema fields changedOct 31, 2026

addedOutput schema / properties / result / properties / substance

Added value: +{
+  "description": "What the score stands on: aspects_total, counts (harmonious, tense, conjunction, minor), tightest {label, orb_deg}, orb_allowed_deg, weighted_strength and confidence (rich, moderate, thin) with its rule in confidence_rule.",
+  "type": "object"
+}

changedOutput schema / properties / result / required

Previous value: -[
-  "token_a",
-  "token_b",
-  "settings",
-  "cross_aspects",
-  "score",
-  "aspect_counts",
-  "tightest",
-  "card"
-]New value: +[
+  "token_a",
+  "token_b",
+  "settings",
+  "cross_aspects",
+  "score",
+  "substance",
+  "aspect_counts",
+  "tightest",
+  "card"
+]

AddedOct 30, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the safety profile is covered. The description still adds substantive context beyond them: deterministic JPL DE440 computation with no LLM, a per-result meta.result_sha256 for verification, a server-rendered card, pandas-ready rows, and the fact that every call costs $0.25 and is never free — the paid/x402 detail is information an agent cannot get from annotations.

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

Conciseness3/5

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

Purpose is front-loaded, but the body is a single dense paragraph that repeats itself ('defined in the response', 'the rule is in the response') and explains response internals at length. Several clauses — the full geometry_score formula and the confidence-label thresholds — duplicate what an output schema already carries and could be trimmed.

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

Completeness4/5

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

For a four-parameter, nested-object tool with an output schema, the description covers what an agent needs: input shape, the launch-time source, determinism, hash verification, and cost/auth path (x402 or MPP, always paid). It slightly over-delivers by narrating return fields the output schema already defines, but nothing essential is missing.

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 description coverage is 100%, so the baseline is 3. The description earns an extra point by showing a concrete token_a/token_b payload with launch_datetime and symbol, and by clarifying that the datetime should be the on-chain block time of contract deployment or mint taken from an explorer — guidance that reinforces how to populate the otherwise loosely-typed oneOf fields.

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: cross-aspects between two tokens' launch skies, with orbs, harmonious/tense counts, a geometry score, and an SVG card. The 'two launch skies' framing plus the example payload makes it distinguishable from the birth-chart sibling 'synastry' and the single-token 'token_chart' without opening any schema.

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

Usage Guidelines3/5

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

Usage is implied by the described output (compat of two launch moments, no houses) and reinforced by the worked example and 'data only — never a signal or forecast'. However, it never explicitly says when to choose this over 'synastry' or 'token_chart', nor any when-not conditions or prerequisites beyond needing a launch block time.

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

All Astro Agents - verifiable planetary timing data and astrology tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.