BrowserMesh

Overview Schema Source Related Servers Discussions Admin

Read page observations

browser_observe

Read-onlyIdempotent

Retrieve bounded browser event logs (console, page errors, network, failed requests) for a specific page, using checkpoints to capture complete evidence.

Instructions

Read bounded observations recorded for one explicitly addressed page. Choose source: 'console' for console events, 'pageError' for uncaught page errors, 'network' for correlated request/response metadata, or 'requestFailed' for transport-level failures. HTTP error responses such as 500 are 'network' response events, not 'requestFailed'. Console and page-error results are metadata-only unless includeText=true, which the network sources reject because they carry no text; exposed text is best-effort redacted and bounded, and console argument objects and raw stacks are never captured. Network URLs remove credentials and fragments and redact sensitive query values; headers, cookies, bodies, storage, WebSockets, service-worker traffic, data URLs, and blob URLs are never captured. Use sinceEventId as a non-destructive checkpoint and inspect gap and droppedCount before treating the evidence as complete.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`pageId`	Yes
`source`	Yes
`sessionId`	Yes
`timeoutMs`	No
`includeText`	No
`sinceEventId`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`gap`	Yes
`events`	Yes
`pageId`	Yes
`source`	Yes
`sessionId`	Yes
`nextCursor`	Yes
`operationId`	Yes
`droppedCount`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.2.2Sep 8, 2026
- removedOutput schema / properties / nextCursor / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / nextCursor / type
```
Added value: +[
+  "string",
+  "null"
+]
```
Addedv0.2.1Aug 19, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Discloses numerous non-obvious behaviors beyond the annotations: observations are bounded, console/page-error results are metadata-only unless includeText=true, text is redacted, many data classes are never captured, and the caller must inspect gap and droppedCount before treating evidence as complete. This goes well beyond readOnlyHint and idempotentHint.

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?

Front-loaded with the verb/resource and source choices, followed by caveats in a logical order. Every sentence adds a new behavioral constraint or clarification without redundancy, despite the high information density.

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?

The description, combined with the output schema and annotations, covers what the tool returns and the critical completeness caveats (gap/droppedCount). No important calling decision appears missing for a read-only observation tool.

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?

With 0% schema description coverage, the description compensates by explaining the source enum values, includeText semantics and why network sources reject includeText, and sinceEventId usage as a non-destructive checkpoint. limit and timeoutMs are not described, but their names and schema constraints are reasonably self-explanatory.

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?

Clearly identifies a specific verb ('Read'), a bounded resource ('observations recorded for one explicitly addressed page'), and enumerates the four observable sources. The description distinguishes this tool from action-oriented siblings like browser_click and browser_navigate, as well as from state-read tools like browser_snapshot.

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

Usage Guidelines4/5

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

Gives explicit source-selection guidance ('console' for console events, 'pageError' for uncaught page errors, etc.) and disambiguates HTTP 500 responses as 'network' rather than 'requestFailed'. It does not explicitly contrast with sibling read tools, but the within-tool source choices are thoroughly specified and supported by edge-case clarifications.

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