create_annotation
Use this when the user wants to add a new annotation to mark a specific date or event in cost data. Changes apply immediately. Do NOT use this for creating labels (use create_label) or alerts (use create_alert).
This record as markdown: /tools/doit/create-annotation.md
What create_annotation does on Doit
AI agents use create_annotation to create or update resources in Doit, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Doit environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
labels | array | — | List of label IDs to associate with the annotation. Labels must already exist. |
content | string | Yes | The content of the annotation (required, non-empty). |
reports | array | — | List of report IDs to associate with the annotation. |
timestamp | string | Yes | Required RFC 3339 timestamp with seconds and a timezone: Z or ±HH:MM (e.g. 2026-01-15T00:00:00Z). Fractional seconds are supported. |
Parameters from the server's own tool schema.
Why create_annotation is rated Medium
An AI agent can call create_annotation faster than any human can review: one bad instruction and it creates or modifies resources in Doit by the hundred, each call as confident as the last.
Risk signalsAccepts raw HTML/template content (content)
Attacks that exploit this kind of access
The rule that runs create_annotation safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Doit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_annotation, this is the rule to start with:
create_annotation stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Doit, apply this rule, and every create_annotation call is checked against it from then on.
Questions about create_annotation
Use this when the user wants to add a new annotation to mark a specific date or event in cost data. Changes apply immediately. Do NOT use this for creating labels (use create_label) or alerts (use create_alert). It is categorised as a Write tool in the Doit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_annotation accepts 4 parameters: labels, content, reports, timestamp. Required: content, timestamp. The full parameter table on this page comes from the server's own tool schema.
Register the Doit MCP server in PolicyLayer and add a rule for create_annotation: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Doit. Nothing to install.
create_annotation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_annotation rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_annotation. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_annotation is provided by the Doit MCP server (@doitintl/doit-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Doit, and thousands of servers like it.
This server
Across the catalogue