Apdf — PDF Tracking & Analytics

Create Automation

create-automation

Create a when/filter/then rule that posts reader events to a webhook. The automation starts out active.

Input Schema

Name	Required	Description
`name`	Yes	Human-readable name for the automation.
`scope`	No	Which documents to watch. Defaults to "all".
`events`	Yes	Reader events that trigger the automation, matched with OR. Pass "*" as the only entry to trigger on every event.
`doc_ids`	No	Public ids of the documents to watch. Required when "scope" is "specific", ignored otherwise.
`conditions`	No	Filters that must all pass before the webhook fires. Not available for an "*" automation.
`webhook_url`	Yes	URL that receives the POST request when the automation fires.
`webhook_headers`	No	Additional headers for the webhook request, as header name => value.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

changedInput schema / properties / events / items / enum

Previous value: -[
-  "*",
-  "document:loaded",
-  "document:download",
-  "document:print",
-  "page:enter",
-  "page:read",
-  "page:leave",
-  "text:copied",
-  "link:clicked",
-  "form:submit",
-  "annotation:create",
-  "annotation:update",
-  "annotation:delete"
-]New value: +[
+  "*",
+  "document:loaded",
+  "document:download",
+  "document:print",
+  "page:enter",
+  "page:read",
+  "page:leave",
+  "text:copied",
+  "link:clicked",
+  "form:submit",
+  "annotation:create",
+  "annotation:update",
+  "annotation:delete",
+  "signature:signed",
+  "signature:declined",
+  "signature:completed"
+]

AddedJul 29, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations only declare destructiveHint=false, so the description carries most of the burden. It adds two real behavioral facts (creates an active rule, fires a POST to the given URL), but says nothing about authentication/permissions, error behavior if the webhook URL is unreachable, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler, and the essential setup behavior (starts active) is placed immediately after the purpose statement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a 7-parameter, nested-object creation call with no output schema, yet the description never indicates what is returned (presumably an automation id) — the very thing an agent needs to later call get-automation, deactivate-automation or delete-automation. The schema is rich, but the post-creation contract is unaddressed.

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 description coverage is 100%, including enum semantics, defaults, the '*' wildcard, and the doc_ids/scope dependency, so the baseline is 3. The description's 'when/filter/then' framing is only a loose map onto events/conditions/webhook and adds no constraint the schema doesn't already state.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource plus the internal structure (when/filter/then) and the effect (posts reader events to a webhook). Clear enough to distinguish from get-automation, list-automations and duplicate-automation, though it never explicitly contrasts with the sibling create/activate pair.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The clause 'The automation starts out active' implicitly tells the agent it need not call activate-automation afterwards, which is useful routing information. However, there is no explicit statement of when to use this versus duplicate-automation or when a user should instead create an inactive rule first.

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

All Apdf — PDF Tracking & Analytics tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?