Skip to content

Editorial: sync explainers with spec (ToolAnnotations link, toolcancel event) #350

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
domfarolino merged 2 commits into from
Oct 16, 2026
Merged

Editorial: sync explainers with spec (ToolAnnotations link, toolcancel event) #350

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
24beb75
Fix broken ToolAnnotations link in security & privacy questionnaire
LF3551 Oct 16, 2026
b334129
Declarative explainer: use toolcancel event name and ModelContext target
LF3551 Oct 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions declarative-api-explainer.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,7 @@ interface SubmitEvent : Event {
};
```

**`toolactivated` and `toolcanceled` events**
**`toolactivated` and `toolcancel` events**

We introduce these events that get fired at the `ModelContext` object when a WebMCP tool is run, and when
its invocation is canceled.
Expand All @@ -183,7 +183,7 @@ form to the user's attention, once a declarative tool is filled out but before i
JavaScript equivalent of the [`:tool-form-active` pseudo-class](#pseudo-classes).

When the agent cancels a tool call (perhaps because a user has instigated another turn of the
conversation, obviating the need for the pending tool), the `toolcanceled` event is fired. Note that
conversation, obviating the need for the pending tool), the `toolcancel` event is fired. Note that
this event does not fire when the site itself cancels the tool, due to removing the form element or
changing its name or description.

Expand All @@ -195,7 +195,7 @@ Some open questions:
> that](https://source.chromium.org/chromium/chromium/src/+/main:third_party/blink/renderer/core/script_tools/model_context.cc;l=265-274;drc=2af6413cf36d701fdaffb09188f2ab2a5be37f4f).

> [!WARNING]
> For declarative, should they be fired at `Window` or at the `<form>` that registered the tool in
> For declarative, should they be fired at `ModelContext` or at the `<form>` that registered the tool in
> the first place, and bubble up to the document that way? See
> https://github.com/webmachinelearning/webmcp/issues/126.

Expand Down
2 changes: 1 addition & 1 deletion security-privacy-questionnaire.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ Yes, origin-supplied tools can influence the user agent's UI in the following wa

- A tool's [`title`](https://webmachinelearning.github.io/webmcp/#dom-modelcontexttool-title) is displayed by the user agent when referencing the tool in its UI.
- Tool responses (the return value of [`execute`](https://webmachinelearning.github.io/webmcp/#dom-modelcontexttool-execute)) may be shown in, or influence, the user agent's UI.
- [Tool annotations](https://webmachinelearning.github.io/webmcp/#dom-modelcontexttoolannotations) can indirectly influence how an agent presents a tool invocation (e.g., a `readOnlyHint` may cause the agent to skip a confirmation step).
- [Tool annotations](https://webmachinelearning.github.io/webmcp/#dictdef-toolannotations) can indirectly influence how an agent presents a tool invocation (e.g., a `readOnlyHint` may cause the agent to skip a confirmation step).

There is also discussion of `requestUserInput` in [Issue #165](https://github.com/webmachinelearning/webmcp/issues/165).

Expand Down
Loading