jevpilot

browser_observe

Reads the current page in an existing browser session without acting. Use full detail when a compact snapshot misses content; returns a screenshot path for handoffs.

Instructions

Read the current page in an existing session without taking action. Use full detail when the compact snapshot omits needed content. A screenshot path may be returned for handoffs when safe.

Input Schema

TableJSON Schema

Name	Required	Description
`detail`	No
`session`	Yes	Session ID returned by browser_run.
`screenshot`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes
`title`	Yes
`trace`	Yes
`usage`	Yes
`reason`	Yes
`status`	Yes
`timing`	Yes
`details`	No
`session`	Yes
`question`	Yes
`snapshot`	Yes
`screenshot_path`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.2.0Oct 1, 2026

changedOutput schema / properties / trace / items / properties / outcome / enum

Previous value: -[
-  "changed",
-  "unchanged",
-  "stale",
-  "covered",
-  "disabled",
-  "invisible",
-  "not-editable",
-  "unstable",
-  "select-failed",
-  "dialog-opened",
-  "value-not-set",
-  "accepted",
-  "dismissed"
-]New value: +[
+  "changed",
+  "unchanged",
+  "stale",
+  "covered",
+  "disabled",
+  "invisible",
+  "not-editable",
+  "unstable",
+  "select-failed",
+  "dialog-opened",
+  "value-not-set",
+  "not-focusable",
+  "accepted",
+  "dismissed"
+]

First observedv0.1.0Sep 29, 2026

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description carries the full disclosure burden. It does signal read-only behavior ('without taking action') and conditional screenshot-return behavior for handoffs, which is valuable behavioral context. It omits permission/auth requirements, whether observation is safe/non-destructive in all cases, and any rate or timing constraints.

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?

Three short sentences with the core read-only purpose front-loaded and no wasted words. The detail guidance and screenshot note follow logically, though the screenshot clause is slightly cryptic.

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?

An output schema exists, so return values need not be spelled out, and the description covers purpose plus one usage guideline. But for a tool with 33% schema coverage and no annotations, it leaves the detail enum and screenshot flag under-specified and does not distinguish clearly from the several sibling browser tools.

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 only 33%, with session documented but detail and screenshot undocumented in the schema. The description compensates partially by referencing 'full detail' and a returned screenshot path, giving the enum and boolean some meaning, but it never defines what 'compact' vs 'full' actually differ in or what screenshot=true produces.

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 ('Read the current page in an existing session') and adds the non-mutating qualifier 'without taking action', which cleanly separates it from the action-oriented sibling browser_act. It does not explicitly name siblings like browser_run or browser_tabs, so differentiation is implied rather than stated.

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?

Gives one actionable guideline ('Use full detail when the compact snapshot omits needed content'), which is genuinely useful for choosing the detail enum. However, it offers no guidance on when to observe versus act, navigate, or run, and no prerequisites or exclusions beyond the implicit session requirement.

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

Deploy Server