ThreadPage

Add a note

create_note

Idempotent

Add a Note at the end of a Thread: new progress, a result, a decision or a question. Find the Thread first (search, list_threads), and prefer one well-structured Note over several fragments. Answers a receipt with the Note's id (entity_id), url and content_revision; the same operation_id answers it again and never adds a second Note. If create_note is your only write tool, omit thread_id: the note goes to the person's Inbox; you cannot read notes. Its receipt then says "delivery": "inbox", with url null: the person's browser collects it.

Example content, a Markdown string:

QA results

Check	Result
Smoke tests	Passed

Fix payment retry
Tag the build

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": {
      "operation_id": "<operation_id>",
      "content": "<content>"
    },
    "name": "create_note"
  }
}

Input Schema

Name	Required	Description
`content`	Yes	The Note's content. A string is Markdown: # Title, ## Heading, ### Subheading; bold, italic, ~~strike~~, `code`; [label](https://…); - bullets and 1. numbered lists (nest under an item's text: 2 spaces after -, 3 after 1.); - [ ] and - [x] checklists (every item needs a box); > quotes; ``` code blocks; pipe tables with a \| --- \| row under the header. A ThreadPage note link alone on its own line becomes a Note reference; ![description](attachment:<attachment_id>) alone on its own line places an image from upload_note_image, and [name](attachment:<file_id>) a file from upload_note_file. No HTML, horizontal rules, underline, colours or tags in Markdown; leave a blank line before a --- line, or the text above it becomes a heading. Or send {"text": "…"} for literal text (its addresses still become links), or {"document": {…}} for a RichDocument as get_note returns it. Markdown up to 32 KiB, 500 lines and 500 of the characters * _ ~ ` < [; a Note up to 256 KiB. Every element: get_guide with topic "formatting".
`thread_id`	No	A Thread's id, from list_threads, search or a read. Omit it to add the Note to the person's Inbox: on Free, the only place a connection adds notes.
`operation_id`	Yes	A new UUID for each write. After a lost answer, send the identical call with the same one, or check get_operation before writing again.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.6/5.0

Behavior4/5

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

With annotations already declaring idempotentHint=true and destructiveHint=false, the description goes further: it describes the receipt shape (entity_id, url, content_revision), the replay behavior with the same operation_id, and the inbox delivery variant where url is null. The idempotency statement largely restates what the annotation already guarantees, which keeps this just short of a 5.

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 prerequisites, then receipt behavior, then the inbox edge case, then an example — a sensible order. The Markdown example is long but earns its space by showing the intended output quality; a few clauses (the Free-plan remark) sit slightly awkwardly inside the thread_id paragraph.

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 three-parameter write tool with no output schema, the description covers what an agent needs: where the note lands, what the response contains, what idempotent replay does, and the degraded inbox path. Nothing material is left to inference.

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, but the description adds semantics the schema does not: what happens when thread_id is omitted (Inbox delivery, url null, Free-plan constraint) and how content is consumed (well-structured Markdown, one note rather than fragments). The embedded Markdown example clarifies content shape without duplicating the schema's syntax list.

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 ("Add a Note at the end of a Thread") and immediately scopes what a note is for (progress, result, decision, question). The placement semantics ("at the end of a Thread") distinguish it from update_note and move_note in the sibling 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?

Explicitly says to locate the Thread first and names the tools to do it (search, list_threads), and advises one well-structured Note over several fragments. It also states the fallback condition precisely: omit thread_id when create_note is the only write tool, and says plainly that the agent cannot read notes back.

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

All ThreadPage tools Inspect

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.