Skip to main content
Glama
DB-25

arc-control-mcp

Start Capture

capture_start
Idempotent

Start recording console output and network activity on an Arc tab for later retrieval by capture_read. Records only from now on, so call again after page navigation.

Instructions

Start recording console output, uncaught errors, unhandled promise rejections and fetch and XMLHttpRequest calls on a tab, for capture_read to return. Records from now on only, and the recorder is lost when the page navigates or reloads, so call it again after. Network events carry method, url, status and duration. Bodies and headers are never recorded, the url fragment is dropped, and the query string is dropped unless include_query is set. Console text IS recorded (capped), so it can hold whatever the page logs. It installs a script into the page's own JavaScript world, because Arc runs this server's scripts in an isolated world that cannot see the page's console or fetch. A page whose Content-Security-Policy forbids inline scripts blocks it: the call then fails with ok false and says why, and network_entries still works. Only the top frame is covered (not iframes or workers), and not WebSockets, sendBeacon or requests made before this call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tab_idNoArc tab id from list_tabs. Omit to use this agent's current tab. A tool that changes a tab will not fall back to the tab the user is looking at, so pass this or call open_url first.
include_queryNoKeep the url query string in network events. Off by default because queries often carry tokens.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations cover readOnlyHint=false and idempotentHint=true, but the description adds rich behavioral context the annotations cannot: recorder lifetime tied to page navigation, CSP blocking behavior with ok false, the isolated-world/JS-world injection rationale, and the data redaction model (no bodies/headers, queries dropped unless include_query, fragments dropped).

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

Conciseness3/5

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

Front-loaded with the primary purpose, which is good. However, the description is a single dense run-on paragraph mixing scope, redaction rules, failure modes, and frame limitations, making it harder to scan than necessary. Length is justified by complexity but structure could be improved with separation.

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?

Given the tool's complexity (session lifetime, CSP failure modes, redaction model, capture surface), the description covers all essential behavioral details an agent needs. No output schema exists, so it correctly points to capture_read for results and network_entries as an alternative for CSP-blocked pages.

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%, so both parameters are already documented in the schema. The description reinforces include_query's effect but does not add syntax or new semantics beyond what the schema provides. Baseline 3 applies.

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?

States a specific verb (Start recording) and enumerates the exact capture surfaces: console output, uncaught errors, unhandled promise rejections, fetch and XHR calls. It also explicitly ties itself to the sibling capture_read as the consumer, and distinguishes from network_entries which still works under CSP block.

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

Usage Guidelines5/5

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

Explicitly says call it again after navigation/reload, mentions the fallback behavior for tab_id vs open_url, and notes what is NOT covered (iframes, workers, WebSockets, sendBeacon, pre-call requests). Gives clear when-to-use and when-not-covered conditions.

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