Skip to main content
Glama

omniseek_search

Read-only

Search curated sources to get ranked, deduplicated, cross-lingual results, then drill into a single source for focused or hard-to-reach coverage.

Instructions

Search the curated sources. The default for "best/latest on X". ONE verb, three shapes.

Tool name: omniseek_search (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_search".

Shapes: default = one ranked, deduped, cross-lingual list; raw=True with exactly one source = an unbounded drill of that source (the way to reach walled or slow sources, which the broad sweep drops at its deadline); raw=True otherwise = uncollapsed per-source buckets.

Args: query: search words; empty browses by recency. sources: source names (None = every non-explicit_only source); take names from omniseek_sources. limit: max documents (per source in buckets). semantic: None = lexical plus vector recall; False = exact tokens only; True = lean on vectors. raw: see shapes. full: whole content per document. wait_s: patience budget in seconds (None = default deadline). staleness: "fresh" (bypass cache) | "cached_ok" (default) | "cache_only" (read what already warmed, send nothing). debug: keep the ranking telemetry in each document's metadata. filters: dict ({"year": {"gte": 2020}}) or expressions ("k=v", "k=a,b", "k>=n", "k=a..b", "k~text"); fields per source in omniseek_sources. as_of: "YYYY-MM-DD" or an ISO time with zone: only items that existed then.

Fire then collect: call with a small wait_s, then again ~20 s later with staleness="cache_only", the SAME query and the SAME limit (limit is in the cache key): faster and more complete.

Returns {query, count, documents, _meta, routing_hint?} (ranked); {source, query, count, documents, _meta?} (one-source drill: _meta.diagnostic when empty or errored, _meta.held when the eye's own gate sent nothing); {query, results: {source: [...]}, total_count, _meta} (buckets). _meta names timed_out / empty / errored / held sources (held = not tried, says nothing about the topic) and excluded_relevant walled sources worth naming. A bad filter returns error, filter_problems and available_filters and sends nothing; a bad as_of returns error. When _meta.web_search_backend shows cooling, wait cooling_s before retrying. More: omniseek docs/TOOLS.md, omniseek_search.

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>"
    },
    "name": "omniseek_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNo
fullNo
as_ofNo
debugNo
limitNo
queryYes
wait_sNo
filtersNo
sourcesNo
semanticNo
stalenessNocached_ok

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.0
    • addedInput schema / properties / as_of
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "As Of"
      +}
    • addedInput schema / properties / filters
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Filters"
      +}
  2. First observedv0.2.0

TDQS

A4.7/5.0
Behavior4/5

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

Annotations only declare read-only; the description carries real extra weight — deadline/staleness behavior, that the broad sweep drops slow sources, that limit is part of the cache key, that a bad filter sends nothing and returns filter_problems, and that a cooling web backend means waiting cooling_s. Some phrasing is idiosyncratic ('the eye's own gate sent nothing'), but the operational traits are disclosed.

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 shapes, then args, then return shapes, then error behavior — a sensible order with no filler. It is dense and occasionally terse to the point of obscurity (quoted jargon, parenthetical asides), which costs a little on first read but nothing is wasted.

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?

No output schema exists, and the description documents all three return shapes, including _meta diagnostics (timed_out/empty/errored/held, excluded_relevant, web_search_backend cooling) and error shapes for bad filters and bad as_of. For an eleven-parameter tool with three modes, nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must carry all eleven parameters, and it does: query (empty = browse by recency), sources (None = all non-explicit_only), limit (per source in buckets), semantic tri-state, raw shapes, full, wait_s, staleness enums, debug, filters mini-grammar with examples, and as_of format. This is meaning well beyond field names and types.

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 ('Search the curated sources') and immediately positions it as 'the default for best/latest on X', which tells an agent both what it does and where it sits among alternatives. The 'three shapes' framing (default / one-source drill / per-source buckets) further pins down the semantics of one verb with three distinct behaviors.

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 rules: use this by default for best/latest, use raw=True with exactly one source to reach walled or slow sources the broad sweep drops at deadline, empty query to browse by recency, staleness='cache_only' for the second poll. It names the sibling (omniseek_sources) for resolving source names and tells the agent how to proceed if the tool is absent from the tool list.

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