Skip to main content
Glama

Update Asset

sirv_update_asset
DestructiveIdempotent

Update one Sirv library asset's file name, alt text, favorite flag, custom metadata, or metadata template; send only changed fields.

Instructions

Change one library asset: its file name, alt text or favourite flag, and its custom metadata fields. Send only what changes.

metadata merges into the asset's fields: the fields you leave out stay. templateId applies a metadata template, and null removes it.

Use it for one asset. To favourite, tag, move, copy, delete or restore many assets, use sirv_bulk_edit_assets. To write alt text with AI, use sirv_generate_alt_text.

It overwrites the values you send. Returns the updated asset, or its metadata when you changed only metadata.

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": {
      "id": "<id>"
    },
    "name": "sirv_update_asset"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesAsset id, from sirv_list_assets
orgIdNoWorkspace id from sirv_list_organizations. Default: the workspace you signed in to
altTextNoNew alt text. An empty string clears it
filenameNoNew file name, with its extension
metadataNoCustom metadata fields to set, by field name. Merges into the existing fields
isFavoriteNotrue to mark the asset as a favourite, false to clear it
templateIdNoMetadata template id to apply to the asset. null removes the template

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv0.1.1
    • changedInput schema / properties / altText / description
      Previous value: -"New alt text"New value: +"New alt text. An empty string clears it"
    • changedInput schema / properties / filename / description
      Previous value: -"New filename"New value: +"New file name, with its extension"
    • changedInput schema / properties / id / description
      Previous value: -"Asset ID"New value: +"Asset id, from sirv_list_assets"
    • changedInput schema / properties / isFavorite / description
      Previous value: -"Favorite status"New value: +"true to mark the asset as a favourite, false to clear it"
    • addedInput schema / properties / metadata
      Added value: +{
      +  "additionalProperties": {
      +    "properties": {
      +      "type": {
      +        "description": "The field type, such as text, number, date or select",
      +        "type": "string"
      +      },
      +      "value": {
      +        "default": null,
      +        "description": "The field value. Default: null"
      +      }
      +    },
      +    "required": [
      +      "type"
      +    ],
      +    "type": "object"
      +  },
      +  "description": "Custom metadata fields to set, by field name. Merges into the existing fields",
      +  "propertyNames": {
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
    • 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)$"
    • addedInput schema / properties / templateId
      Added value: +{
      +  "description": "Metadata template id to apply to the asset. null removes the template",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds real semantics beyond them: partial-update behavior ('Send only what changes'), merge rather than replace for metadata, null-based template removal, and what is returned. It does not discuss permissions or whether filename changes break existing CDN URLs, which matters for a destructive mutation.

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 purpose, then merge semantics, then routing to siblings, then return shape and cost. Tight overall, though 'Send only what changes' and 'It overwrites the values you send' partially restate the same partial-update idea and could be merged.

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?

For a 7-parameter mutation with a nested metadata object and no output schema, the description covers scope, merge semantics, template handling, return values, and cost. An agent has enough to invoke it correctly without opening the schema.

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 every parameter including the nested metadata object is already documented at the schema level, and the description's merge/null notes closely mirror the schema text. The only genuine addition is the 'send only what changes' framing, which is marginal on top of a fully documented 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?

States a specific verb and resource ('Change one library asset') and enumerates exactly which attributes are mutable: file name, alt text, favourite flag, custom metadata. It explicitly scopes to a single asset, which cleanly separates it from sirv_bulk_edit_assets.

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?

Gives an explicit when-to-use ('Use it for one asset') plus two named alternatives with the conditions that select them: bulk operations go to sirv_bulk_edit_assets, AI alt text goes to sirv_generate_alt_text. 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.