Skip to main content
Glama

Update Sirv File Metadata

sirv_cdn_update_file_metadata
Destructive

Update metadata for one Sirv CDN file: set title, description, product fields, and tags; omitted values stay unchanged.

Instructions

Change the metadata of one file in the connected Sirv account, at file_path. Send any of title, description, product, add_tags and remove_tags. The fields you leave out stay as they are.

title, description and the product fields take the new values. Sirv uses the description as the image's alt text. add_tags adds tags and keeps the others. remove_tags removes only the tags you name.

These are files in the Sirv account connected to the workspace, not Studio library assets. For a library asset, use sirv_update_asset. To rename, copy or delete the file, use sirv_cdn_manage_file. Read the current values first with sirv_cdn_get_file_metadata; Studio keeps no copy of the old title or description.

Studio queues the change and Sirv applies it in the background, so a read straight after can still show the old values. Returns the queued change.

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": {
      "file_path": "<file_path>"
    },
    "name": "sirv_cdn_update_file_metadata"
  }
}

Input Schema

NameRequiredDescriptionDefault
orgIdNoWorkspace id from sirv_list_organizations. Default: the workspace you signed in to
titleNoNew title, up to 256 characters
productNoProduct fields to set on the file
add_tagsNoTags to add, up to 50 of 32 characters each. The file keeps its other tags
file_pathYesFull path of the file in Sirv, such as /products/hero.jpg
descriptionNoNew description, up to 1024 characters. Sirv uses it as the image's alt text
remove_tagsNoTags to remove, up to 50. The file keeps its other tags

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changedv0.1.1
    • addedInput schema / properties / add_tags
      Added value: +{
      +  "description": "Tags to add, up to 50 of 32 characters each. The file keeps its other tags",
      +  "items": {
      +    "maxLength": 32,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "maxItems": 50,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / description / description
      Added value: +"New description, up to 1024 characters. Sirv uses it as the image's alt text"
    • changedInput schema / properties / file_path / description
      Previous value: -"Full Sirv file path, such as /products/hero.jpg"New value: +"Full path of the file in Sirv, such as /products/hero.jpg"
    • 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 / product / description
      Added value: +"Product fields to set on the file"
    • addedInput schema / properties / product / properties / brand / description
      Added value: +"Brand"
    • addedInput schema / properties / product / properties / category1 / description
      Added value: +"Top-level category"
    • addedInput schema / properties / product / properties / category2 / description
      Added value: +"Second-level category"
    • addedInput schema / properties / product / properties / id / description
      Added value: +"Product id or SKU"
    • addedInput schema / properties / product / properties / name / description
      Added value: +"Product name"
    • addedInput schema / properties / remove_tags
      Added value: +{
      +  "description": "Tags to remove, up to 50. The file keeps its other tags",
      +  "items": {
      +    "maxLength": 32,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "maxItems": 50,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • removedInput schema / properties / tags
      Removed value: -{
      -  "description": "Replaces the file's tags",
      -  "items": {
      -    "maxLength": 32,
      -    "minLength": 1,
      -    "type": "string"
      -  },
      -  "maxItems": 50,
      -  "minItems": 1,
      -  "type": "array"
      -}
    • addedInput schema / properties / title / description
      Added value: +"New title, up to 256 characters"
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only flag destructive=false/readOnly=false, so the description carries the real behavioral load and does: partial-update semantics (omitted fields stay), additive vs. subtractive tag behavior, async background application with possible stale reads immediately after, and what the call returns (the queued change). It also states there is no credit cost. None of this is inferable from the annotations.

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 action and path, then scoping, prerequisites, async caveat, and cost in short paragraphs. A few lines restate behavior the schema already spells out (the tag descriptions duplicate add_tags/remove_tags), and "Credits: free" is a minor add-on, but nothing is genuinely 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?

For a 7-parameter mutation with a nested product object and no output schema, the description covers the essential unknowns: merge vs. replace semantics, async application timing, and the return value. An agent has everything needed to call it correctly and interpret the result.

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 100%, so the baseline is 3; the description earns more by explaining merge semantics the schema does not state ("The fields you leave out stay as they are", add_tags keeps existing tags, remove_tags removes only named tags) and by noting Sirv uses the description as alt text. It does not elaborate on `orgId` or the nested product fields, which remain schema-only.

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?

Opens with a specific verb and resource ("Change the metadata of one file") and pins the scope with `file_path`. It explicitly distinguishes these files from Studio library assets and names sirv_update_asset and sirv_cdn_manage_file as the tools for those other cases, so an agent can separate it from siblings without opening a 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?

States when to use this tool and when not to: use sirv_update_asset for library assets, sirv_cdn_manage_file for rename/copy/delete. It also recommends reading current values first with sirv_cdn_get_file_metadata and gives the reason (Studio keeps no copy of old values), which turns a suggestion into an actionable prerequisite.

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