Skip to main content
Glama

omniseek_gather

Read-only

Run up to 10 independent read-only searches, transcriptions, or visual reads in parallel and get combined results in one response, with an optional wait time for unfinished calls.

Instructions

Run N independent read-only eye tools IN PARALLEL, returning results in one response.

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

Args: calls: [{"tool": "omniseek_search", "args": {...}}, ...]: at most 10, read-only tools only; a call that needs another's result goes in a later gather. wait_s: return when all finish or after this many seconds; unfinished calls report status "warming" and keep running (collect later with staleness="cache_only", or repeat the same omniseek_transcribe).

Calls through one rate-gated upstream (several arXiv reads, say) run one after another at its pace; more than 2 search-index venues in one gather adds a warning. Returns {results: [{index, tool, status, result | error | hint}], elapsed_s, completed, warming, failed, total}; a wrong argument's hint names the tool's real parameters. More: omniseek docs/TOOLS.md, omniseek_gather.

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": {
      "calls": "<calls>"
    },
    "name": "omniseek_gather"
  }
}

Input Schema

NameRequiredDescriptionDefault
callsYes
wait_sNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true, but the description adds substantial behavior: calls through one rate-gated upstream serialize, more than 2 search-index venues triggers a warning, unfinished calls report status 'warming' and keep running with a documented recovery path (staleness="cache_only" or repeat). It also discloses the exact return shape and the hint field for bad arguments.

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 behavior in the first line, then structured into args, execution caveats, and return value. Some lines (MCP prefix warning, ToolSearch fallback, docs pointer) are operational boilerplate, but none of it is padding for an agent that may need to resolve the name.

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 no output schema, the description supplies the full response shape ({results with index/tool/status/result|error|hint, elapsed_s, completed, warming, failed, total}), plus the async 'warming' contract an agent must handle. Nothing essential for calling or interpreting the result appears 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 coverage is 0%, so the description carries the load, and it does: calls is explained as an array of {tool, args} with a worked example, a hard cap of 10, and a read-only restriction, while wait_s is defined as the cutoff after which unfinished calls go to 'warming' rather than aborting. Per-call args are left to each sub-tool's own schema, which is reasonable but leaves the nested object loosely specified.

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 concrete verb and resource: run N independent read-only tools in parallel and return results in one response. The parallel fan-out framing immediately distinguishes it from the single-tool siblings (omniseek_search, omniseek_read, etc.) without needing their schemas.

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

Usage Guidelines4/5

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

Gives real selection rules: at most 10 calls, read-only tools only, and 'a call that needs another's result goes in a later gather' — an explicit when-not condition. It stops short of saying when to prefer a single direct tool call over gathering, but the dependency and read-only constraints cover most routing decisions.

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