Ontonym

Semantic search

semantic_search

Read-onlyIdempotent

Search a memory's classes and objects — meaning AND keywords.

Two rankers run and their results are fused: a vector leg that matches by
meaning (finds the paraphrase) and a keyword leg that matches the literal
words (finds the rare token a vector smooths away — an error code, a
surname, a part number). Each hit carries `via` saying which legs found
it; a hit both agreed on is a stronger answer than one matched on
keywords alone. Ties break toward the NEWER row.

Because the keyword leg needs no index, search still answers on a memory
that was never embedded — with a `note` saying the semantic half was
unavailable. `memory` is the slug from list_my_memories. `kind` =
'class' | 'object' | omit. Check `status` and defer on 'unapproved'.

`expand=1` inlines each top object hit's FIRST RING — properties plus
relationship groups with counts and member previews — so you learn what a
hit is and what it touches without a get_object per hit. Prefer expand=1
whenever you intend to follow relationships; for reach beyond one ring,
use get_paths instead of hopping get_object calls.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`kind`	No
`query`	Yes
`top_k`	No
`expand`	No
`memory`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 11, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare read-only/idempotent/non-destructive, but the description adds substantial behavior beyond them: two fused rankers, the `via` field indicating which leg matched, newer-row tie-breaking, and graceful degradation with a `note` when the memory was never embedded.

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 with the core mechanic and then progressively detailed, with every sentence carrying information. Slightly ornate phrasing ('the rare token a vector smooths away') costs a little density but remains purposeful.

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?

An output schema exists, so return formatting need not be spelled out, yet the description still explains the meaningful return-shape signals (`via`, `note`, `status`). For a 5-param search tool this covers everything an agent needs to invoke it correctly.

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 0%, so the description must compensate, and it does for most params: `memory` (slug from list_my_memories), `kind` ('class'|'object'|omit), and `expand=1` (inlines first-ring properties and relationship groups). It leaves `top_k` and `query` semantics unstated, a minor gap.

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+resource (search a memory's classes and objects) and immediately explains the dual-ranker mechanism, which differentiates it from siblings like recall or list_objects. An agent can distinguish it from get_object/get_paths without opening a schema.

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?

Explicit routing: 'Prefer expand=1 whenever you intend to follow relationships; for reach beyond one ring, use get_paths instead of hopping get_object calls.' Also gives prerequisites (memory slug from list_my_memories, check status and defer on 'unapproved').

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

All Ontonym 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.

Resources

Need Help?