omniref

Search References

search_references

Read-only

Search images and videos across multiple providers in one call, returning normalized, deduplicated results. Restrict by media type or provider; partial failures appear in errors.

Instructions

Search images and videos across all providers; results are normalized and deduplicated.

Partial failures are reported in errors while other providers' results are still returned.

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": "search_references"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max results per provider.
`query`	Yes	What to look for, e.g. 'handheld night street, neon, rain'.
`providers`	No	Provider names from list_providers. Default: all.
`media_types`	No	Restrict to 'image' and/or 'video'. Default: both.

Output Schema

Name	Required	Description
`query`	Yes
`errors`	No	Providers that failed. Partial results are still returned.
`results`	Yes
`providers_queried`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover read-only and open-world semantics, yet the description adds genuine behavior beyond them: results are normalized and deduplicated, and partial provider failures surface in `errors` while other results still return. That failure-tolerance detail is exactly the kind of context annotations cannot express.

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?

Two short sentences, front-loaded with the core action, with the normalization/dedup trait before the error-handling caveat. No filler or restated title.

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

Completeness4/5

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

Since an output schema exists, return structure needn't be spelled out, and the description still correctly explains the `errors` field's semantics. Minor gap: no mention of how results from multiple providers are ordered or capped beyond the schema's limit.

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 all four parameters (query, limit, providers, media_types) are already documented in the schema. The description's 'across all providers' loosely echoes the providers default but adds no new parameter meaning, so the baseline of 3 applies.

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

Purpose4/5

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

Names a specific verb and resource ('Search images and videos') plus a scope ('across all providers') and a result property ('normalized and deduplicated'). It doesn't explicitly contrast with the only sibling, list_providers, though the distinction is reasonably inferable from 'search across all providers'.

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

Usage Guidelines3/5

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

Usage is only implied by the purpose statement; there is no explicit when-to-use, when-not, or pointer to list_providers for provider discovery (which the schema references but the description does not). An agent can infer intent but gets no routing guidance.

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

Deploy Server