Skip to main content
Glama

Robot Actions — Remote Device Control

ios_safari_capture_network

Capture network requests made by a Safari page on an iOS device over a time window. Collects Network.requestWillBeSent, Network.responseReceived, Network.loadingFinished, and Network.loadingFailed events and returns merged records. Returns { records, bodiesOmitted? } in summary format, or a HAR 1.2 document when format="har". Each record: { requestId, method, url, requestHeaders?, status?, statusText?, mimeType?, resourceType?, responseHeaders?, encodedDataLength?, state, errorText?, startTimestamp?, endTimestamp?, body?, bodyTruncated?, bodyError? }. Set includeBodies=true to fetch response bodies for completed text-like responses (json|text|xml|javascript|html|css|svg|x-www-form-urlencoded); per-body cap: 10 000 chars (bodyTruncated=true when hit); total cap: 200 000 chars (excess records counted in bodiesOmitted). Body fetch failures set bodyError on that record. Set throttle to emulate bandwidth for the capture window only (best-effort; cleared afterwards): slow-3g (51 200 B/s) or fast-3g (209 715 B/s). NOTE: throttle="offline" is NOT supported on iOS — WebKit only has bandwidth throttling; use android_devtools_capture_network for offline. When throttle was active, a top-level throttle field appears in the output. Returns at most limit records (default 100, most-recent first) so heavy pages stay within the token budget — filter with urlSubstring / onlyErrors; total/returned appear when records were dropped. Default window: 5 000 ms. Maximum: 30 000 ms. Omit pageId to auto-pick the active page. Pass url to navigate inside the capture session and record the full page-load waterfall (pass the current URL to reload).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoNavigate the page to this URL inside the capture session to record the full page-load waterfall (pass the current URL to reload)
udidYesiOS device UDID
limitNoMax records to return, most-recent first (default 100). Heavy pages make hundreds of requests; the default keeps the response within the MCP token budget. total/returned are included when records were dropped.
formatNoOutput format: "summary" (default) returns { records, bodiesOmitted? }; "har" returns a HAR 1.2 document
pageIdNoCDP target id from ios_safari_list_pages. Omit it to use the page ios_safari_navigate last landed on (or, failing that, the first loaded page) — only pass it to target a DIFFERENT tab
throttleNoEmulate bandwidth for the capture window only (best-effort; cleared afterwards). slow-3g: 51 200 B/s. fast-3g: 209 715 B/s. offline is NOT supported on iOS — use android_devtools_capture_network instead.
triggerJsNoJavaScript run INSIDE the capture window (after the collector attaches) to trigger requests race-free — e.g. "fetch('/api/x')" or a click. For a full-page navigation prefer the `url` param. Both avoid the attach-race of triggering from a separate call.
durationMsNoCollection window in milliseconds (default: 5000, max: 30000)
onlyErrorsNoOnly failed / 5xx records
urlSubstringNoOnly records whose URL contains this substring — target the requests you care about
includeBodiesNoFetch response body for completed text-like responses (default: true). Request bodies (postData) are always captured. Set false to skip response bodies for a lighter payload. Per-body cap: 10 000 chars. Total cap: 200 000 chars.
platformVersionNoIgnored (kept for compatibility)

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses output structure, body truncation caps (10k/200k chars), bodiesOmitted behavior, best-effort throttle with cleanup, unsupported offline mode, default/max duration, auto-selection of pageId, and token-budget rationale for the limit parameter. These are behavioral details beyond basic semantics.

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?

The description is long, but every sentence provides essential operational detail for a tool with 12 parameters and no output schema. It is front-loaded with the core purpose and progressively adds details in a logical order (output, bodies, throttle, limit, window, page selection). No filler or repetition.

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 tool is complex and has no output schema, yet the description explains the complete return shape ({ records, bodiesOmitted? }, per-record fields, HAR option), all relevant caps, fallback behaviors, and edge cases (e.g., offline unsupported, pageId fallback). An agent can fully understand preconditions, usage, and expected results from this description alone.

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?

Schema coverage is 100%, so baseline is 3. However, the description adds meaning beyond the schema: it explains the record format (requestId, method, url, etc.), the meaning of bodyTruncated/bodyError, how bodiesOmitted appears, and the interaction between url and the capture session. Some of this overlaps with schema descriptions, but the record structure and composite behaviors add value.

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?

The description clearly states the verb and resource: 'Capture network requests made by a Safari page on an iOS device over a time window.' It specifies exactly what events are collected and even distinguishes itself from the Android counterpart by noting the offline throttle limitation.

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?

The description provides explicit guidance on when to use this tool, including an explicit alternative: 'use android_devtools_capture_network for offline.' It also explains best practices for filtering (urlSubstring, onlyErrors), triggering requests (url or triggerJs), and formatting output (summary vs har).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0
Disambiguation2/5

The set contains near-identical duplicate families: web_* and playwright_* expose ~15 pairs of the same desktop-grid-browser operations (web_get_text/playwright_get_text, web_reload/playwright_reload), and screenshot/log/network/mock capabilities each have 5-8 entry points (device_screenshot vs android_mjpeg_screenshot vs ios_screenshot vs ios_fast_screenshot vs web_screenshot vs webpage_screenshot vs session_screenshot). Many individual descriptions carefully draw boundaries (devtools vs traffic, HID vs session), but an agent cannot reliably distinguish web_* from playwright_*, and ios_screenshot/ios_fast_screenshot/ios_mjpeg_screenshot blur together.

Naming Consistency2/5

The prefix scheme is broken: Android functionality is split arbitrarily between android_* and device_* (device_screenshot vs android_mjpeg_screenshot), the desktop browser gets two parallel prefixes (web_* and playwright_*), and verbs vary across equivalents (device_navigate_url vs web_navigate vs ios_safari_navigate). session_* uses bare verbs (session_url, session_back), and the same concept gets different names (ios_clipboard_get_hid vs ios_get_pasteboard; device_screen vs ios_orientation).

Tool Count1/5

333 tools is an extreme count by any measure — far beyond the 50+ threshold — and much of the bulk is duplicative (the web_*/playwright_* pairs alone double ~15 slots) or out-of-scope for a device-control server (TestRail, Jira, AzDO, agent memory, secret variables, feedback). Even granting that remote device control + test automation is a broad domain, this surface will devastate agent context budgets and is impossible to navigate coherently.

Completeness4/5

The core device-control and test-automation domain is remarkably thorough: Android and iOS each have full interaction, app-lifecycle, file, network/proxy, performance, crash, accessibility, recording, and replay coverage, with CRUD lifecycles for flows, suites, app uploads, TestRail cases, and visual-review baselines. Minor gaps exist at the margins — Jira/AzDO lack update/transition/comment operations, and iOS cannot open/close tabs — but the central workflows have no dead ends.

Resources