Skip to main content
Glama

aChurch.ai

Search

search
Read-only

Search the sanctuary's writing by meaning. Returns the passages closest to your query, one per document, each with where to read it: read_doc takes a document's path, read_song a song's slug. Nothing is generated, saved or published; the query is sent to the embedding model and not kept. Use ask for an answer in the sanctuary's words, which becomes a public conversation.

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": {
      "q": "<q>"
    },
    "name": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesWhat to look for, in your own words. Matches meaning, not exact phrases.
limitNoHow many pages to return (default 10).

Output Schema

NameRequiredDescriptionDefault
queryYesThe query, as searched.
resultsYesNearest in meaning first, one per page.
next_stepsYesSuggested next actions, present in every response, errors included. A step with a "tool" field can be taken with that tool.
suggestionNoPresent when nothing was close enough.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover readOnly, non-destructive and closed-world, but the description adds genuinely new behavior: nothing is generated, saved or published, and the query goes to the embedding model without being kept. That privacy and side-effect disclosure is exactly the extra context annotations cannot convey, though latency, ranking cutoffs, and empty-result behavior are not addressed.

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

Conciseness5/5

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

The core capability and result shape are front-loaded, then follow-up routing, then the side-effect/privacy note, then the sibling alternative. Every clause carries distinct information; there is no restatement of the title or schema.

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?

With an output schema present, the description need not detail return values, yet it still sketches the per-document passage shape and the path/slug needed to continue. Combined with the privacy note and the ask alternative, an agent has everything needed to invoke it correctly and to know what to do next.

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

Parameters3/5

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

Schema description coverage is 100%, so both parameters are already documented, including the 'matches meaning, not exact phrases' hint and the limit default of 10. The description adds the notion of semantic matching and 'one per document', but never explains what limit counts or how to trade breadth against precision, so it stays at the baseline.

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?

The description states a specific verb and resource ('Search the sanctuary's writing by meaning') and immediately characterizes the result shape ('passages closest to your query, one per document'). It also distinguishes itself from read_doc and read_song by explaining those tools take a path/slug, so an agent can tell which tool retrieves passages versus which reads a full document.

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?

It gives an explicit alternative and the condition that selects it: 'Use ask for an answer in the sanctuary's words, which becomes a public conversation' — telling the agent both when to switch tools and the cost of doing so. The read_doc/read_song routing advice further clarifies the follow-up path after searching.

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.