Skip to main content
Glama
astroway-mcp

astroway-mcp

Official
by astroway

MCP RAG Search

astroway_mcp_rag_search
Read-onlyIdempotent

Retrieves relevant chart passages by keyword-tag scoring so you can match a query against a natal chart and get the top-ranked chunks.

Instructions

Keyword-tag scoring over chart chunks.

[Group: MCP Advanced] [Endpoint: POST /v1/mcp/rag-search] [Required: query, chart] [Cost: 10 credits (Tier 1)]

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": {
      "query": "<query>",
      "chart": "<chart>"
    },
    "name": "astroway_mcp_rag_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
topKNo
chartYesBirth data for a single natal chart. Required: date (YYYY-MM-DD), time (HH:mm:ss), latitude and longitude in decimal degrees. The short forms lat, lon, lng and tz are rejected with 400 INVALID_FIELD; pass the full names. timezoneOffset is hours from UTC and defaults to 0, meaning UTC; send timezone instead (an IANA name such as Europe/Kyiv, or auto) and the offset for that date is worked out, summer time included. city is a display label only: nothing here geocodes it, so it never stands in for coordinates. houseSystem is a single house-system letter, P by default; a name such as "Placidus" is refused, and the case matters because I and i are two different Sunshine systems.
queryYes

Output Schema

NameRequiredDescriptionDefault
queryNo
totalNo
tokensNo
matchesNo
resultsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.6.1
    • changedInput schema / properties / chart / description
      Previous value: -"Birth data for a single natal chart. Required: date (YYYY-MM-DD), time (HH:mm:ss), latitude and longitude in decimal degrees. The short forms lat, lon, lng and tz are rejected with 400 INVALID_FIELD; pass the full names. timezoneOffset is hours from UTC and defaults to 0, meaning UTC; send timezone instead (an IANA name such as Europe/Kyiv, or auto) and the offset for that date is worked out, summer time included. city is a display label only: nothing here geocodes it, so it never stands in for coordinates. houseSystem is a single Swiss Ephemeris letter, P by default; a name such as \"Placidus\" is refused, and the case matters because I and i are two different Sunshine systems."New value: +"Birth data for a single natal chart. Required: date (YYYY-MM-DD), time (HH:mm:ss), latitude and longitude in decimal degrees. The short forms lat, lon, lng and tz are rejected with 400 INVALID_FIELD; pass the full names. timezoneOffset is hours from UTC and defaults to 0, meaning UTC; send timezone instead (an IANA name such as Europe/Kyiv, or auto) and the offset for that date is worked out, summer time included. city is a display label only: nothing here geocodes it, so it never stands in for coordinates. houseSystem is a single house-system letter, P by default; a name such as \"Placidus\" is refused, and the case matters because I and i are two different Sunshine systems."
  2. Addedv1.6.0

TDQS

C2.7/5.0
Behavior3/5

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 useful operational context beyond that: a fixed cost of 10 credits (Tier 1), the HTTP endpoint, and the required inputs. It says nothing about how scoring works, ranking order, or what happens with an empty result set.

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?

The single purpose sentence is front-loaded and the bracketed metadata block is scannable. The "Required" tag duplicates the schema's required array, which is the only real waste.

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

Completeness2/5

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

An output schema exists, so return-value description is not owed, but the tool is a nested-object retrieval call with two undocumented top-level parameters. Nothing tells the agent what corpus is searched, how the chart argument scopes it, or how results are ordered, leaving the definition thin for its complexity.

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

Parameters2/5

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

At 33% schema coverage, the description needs to compensate and does not: it only restates that query and chart are required, which the schema already enforces. Neither query (free text? keywords? natural language?) nor topK (default 5, max 20) is explained, and the description never connects the query string to the "keyword-tag" scoring it advertises.

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

Purpose3/5

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

"Keyword-tag scoring over chart chunks" names a mechanism and a resource, but never states plainly that this is a retrieval/search operation or what it returns to the caller. It is distinguishable from agent-orchestration siblings only by inference, not by an explicit contrast in the text.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no when-not-to-use, and no named alternative among the many sibling tools (e.g. multi_chart_context, ai_interpret_natal) that also consume chart data. The agent must guess whether this is the right retrieval entry point.

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

Deploy Server

Other Tools