Skip to main content
Glama

View attachment images

view_attachment_images
Read-only

Show image attachments to you, the model. Pass media_id from list_attachments (or the id in a /media/ URL) as one string or a list of 1–10 IDs; results come back per distinct ID in input order. Only images up to 25 MB: other kinds, larger images and unavailable files come back as per-item errors. In a client that renders MCP Apps widgets, the Werify widget sends you the images as the next message, after you end your turn: end it promptly and do not fetch the URLs. In other clients, each result's url downloads the original image without Authorization or cookies until expires_at, for a tool of yours that fetches files or for the user. Anyone holding the URL can download that file until it expires; do not publish it. The result's first text says which case this is.

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": {
      "media_id": "<media_id>"
    },
    "name": "view_attachment_images"
  }
}

Input Schema

NameRequiredDescriptionDefault
media_idYesOne media_id of an image from list_attachments (or a /media/<id> URL), or a list of 1–10 IDs.

Output Schema

NameRequiredDescriptionDefault
localeNoThe Werify account's language as a BCP 47 tag, for the widget's own text.
resultsNoOne image or error per distinct media_id, in input order.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Goes well past the readOnly/non-destructive annotations: per-distinct-ID results in input order, per-item errors for wrong kind/oversized/unavailable files, URL expiry via expires_at, and the warning that anyone holding the URL can download the file. The one gap is that the widget interaction is described in procedural terms without stating what the agent sees if it ignores the 'end your turn' instruction beyond 'first text says which case this is'.

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 purpose, then limits, then client-specific behavior — a sensible order with no filler sentences. It is admittedly dense and runs long for one tool, but each clause carries operational information (size cap, expiry, secrecy) that the agent would otherwise have to discover by error.

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 one-parameter read tool with an output schema, the description covers everything the agent must decide before calling: which IDs, how many, what fails, and what to do with the returned url or widget message. Return-value structure is rightly left to the output schema, so nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, but the description adds real semantics: accepted ID provenance (list_attachments or /media/<id> URL), the 1–10 cardinality, and that output is keyed per distinct ID in input order. That dedup/ordering contract is not expressible from the schema alone and directly affects how an agent batches IDs.

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 — 'Show image attachments to you, the model' — and immediately routes ID sourcing to list_attachments (or a /media/<id> URL), distinguishing it from the file-listing sibling. An agent knows exactly what it gets back (the images themselves) versus a metadata list.

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 the precondition (media_id from list_attachments), the limits that select the error path (images only, ≤25 MB), and two explicit client-dependent usage modes: end the turn promptly in widget clients and do not fetch URLs, versus use the result url in other clients. This is when/when-not/alternative guidance rather than implied context.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources