Skip to main content
Glama

Find Similar Assets

sirv_find_similar_assets
Read-onlyIdempotent

Finds library assets visually similar to a specified asset, ranking matches by similarity score to help identify duplicates or alternate shots of the same product.

Instructions

Find library assets that look like one asset, ranked by visual similarity.

Use it to find duplicates or other shots of the same product. Do not use it for a search by words (use sirv_list_assets with q) or for files in the connected Sirv account (use sirv_cdn_search_files).

Inputs: assetId, the library asset to match, is required. limit is 1 to 50 (default 20).

It needs visual similarity in the workspace plan; without it, the tool returns an error. Read-only. Returns the matching assets with their ids, file names, types and a similarity score, best match first.

Credits: free.

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": {
      "assetId": "<assetId>"
    },
    "name": "sirv_find_similar_assets"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMatches to return, 1 to 50. Default: 20
orgIdNoWorkspace id from sirv_list_organizations. Default: the workspace you signed in to
assetIdYesId of the asset to match, from sirv_list_assets

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.1
    • changedInput schema / properties / assetId / description
      Previous value: -"Asset ID to use as the visual search seed"New value: +"Id of the asset to match, from sirv_list_assets"
    • changedInput schema / properties / limit / description
      Previous value: -"Number of visually similar assets to return"New value: +"Matches to return, 1 to 50. Default: 20"
    • changedInput schema / properties / orgId / description
      Previous value: -"Organization ID (uses default org if omitted)"New value: +"Workspace id from sirv_list_organizations. Default: the workspace you signed in to"
    • addedInput schema / properties / orgId / pattern
      Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent and non-destructive behavior, and the description goes further: it discloses the plan prerequisite for visual similarity and that a missing entitlement produces an error, states the result ordering ('best match first'), the returned fields, and that the call burns no credits. That is exactly the behavioral 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?

Front-loaded with the core function, then usage routing, then inputs, then constraints, then cost — each in a single short block. No sentence is redundant with another, and the facts an agent needs before calling arrive first.

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 compensates by enumerating the returned fields and ordering. Combined with the plan/error caveat, input summary and credit note, an agent has everything needed to decide and invoke correctly.

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 coverage is 100%, so all three parameters are already documented, including the limit bounds and default and the assetId provenance. The description restates the assetId/limit semantics rather than adding new meaning, so it sits at the baseline for a fully-described schema.

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?

A specific verb and resource ('Find library assets that look like one asset, ranked by visual similarity') plus a scope qualifier ('library assets', not CDN files) lets an agent separate it from sirv_list_assets and sirv_cdn_search_files without opening either 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 positive case ('find duplicates or other shots of the same product') and two explicit exclusions with the correct alternative named for each (word search -> sirv_list_assets with q; connected-account files -> sirv_cdn_search_files). Nothing is left to inference.

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