Skip to main content
Glama
Sign In

ThreadPage

by page.thread
OverviewDiscussionsAdmin

Look at an image in a note

read_note_attachment
Read-onlyIdempotent

See an image in a Note: a preview with its metadata removed, not the original file (a PNG up to 1600 px and 1 MiB; for a larger image or another format, its WebP or JPEG preview up to 2048 px). One still being prepared answers timed_out: retry after details.retry_after. For other files in a Note, use read_note_file. Previews count toward a per-minute and a daily limit.

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": {
      "note_id": "<note_id>",
      "attachment_id": "<attachment_id>"
    },
    "name": "read_note_attachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
note_idYesA Note's id, from get_thread, search or get_note.
version_idNoTo read the image of an old version: A version's id, from get_note_history.
attachment_idYesAn image's id, from get_note's images.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior3/5

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

The annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description then adds genuinely useful context the annotations cannot convey: preview dimensions and size ceilings, format fallbacks, a timed_out state with details.retry_after, and per-minute plus daily rate limits. It stops short of describing the actual response payload or how the preview is delivered, which keeps it out of the top band given how much the annotations already carry.

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?

Roughly four dense sentences, front-loaded with what the tool returns before the caveats and the sibling pointer. Minor awkwardness ('One still being prepared answers timed_out') costs it the top band, but nothing is padding.

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?

With no output schema, the description does the work of explaining what comes back (a downsized preview, not the original) and how a pending result surfaces. Combined with the rate limits and the sibling pointer, an agent has almost everything it needs; only the exact response shape or image delivery mechanism is left implicit.

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% and every parameter (note_id, version_id, attachment_id) is already documented with its source tool. The description adds no syntax, format, or edge-case detail for any of the three, so the baseline of 3 applies.

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 ('See an image in a Note') and immediately narrows scope: it returns a preview with metadata stripped, not the original file. It explicitly contrasts itself with the sibling read_note_file for other file types, so an agent can choose correctly 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?

Routing is explicit: images go here, other files go to read_note_file, and old versions are reachable via version_id. It also tells the agent what to do on a non-final state (timed_out) and where to find the retry delay.

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

All ThreadPage toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources