Skip to main content
Glama
AceAtDev

ascended-browser

by AceAtDev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

browser_act

Perform one verified browser action—navigate, click, fill, select, check, press, upload, scroll, or wait—in a leased tab, returning fresh refs or confirming the page is unchanged.

Instructions

Perform one verified action in a leased tab. action.kind must be navigate|click|fill|fill_form|sequence|select|check|date|press|upload|scroll|wait (action.type is accepted as an alias for kind; type=type means fill). ref must be an exact ref=e… token from the newest page/observe/extract result for this tab — labels and row numbers are rejected; CSS/XPath/text selectors are not an agent-facing escape hatch. Reuse the fresh refs returned in an action's page; do not observe again after every field. A successful act returns either page (the page it produced, with fresh refs) or page_unchanged: true, meaning the URL and visible text are what your last observation showed and its refs still apply — observe again only for a different view (query, selector, region). Batch stable fields with fill_form, which reports each field separately. For anything that picks from a list (native selects, custom ARIA comboboxes and dropdowns, type-to-search boxes) use kind=select with option= and optional query=; this performs and verifies open/filter/choose in one call. For anything with a checked or selected state, including list items, use kind=check with checked=true|false. Independent calls for distinct tab_ids may be issued together; calls targeting one tab remain ordered. Use sequence for a short reversible multi-step workflow when later-page targets can be named semantically. Every step is re-resolved from current page state, authority is rechecked, and the sequence stops before dispatch when an exact expect_before guard or a unique target is missing; use expect_after to guard a planned transition. Do not place a consequential final submit in a sequence. until waits inside the call for a late effect (redirect, async save, hot reload); kind=wait only waits. The same select fields can be included in fill_form. For a reversible draft/save action, a click receipt with state=network_effect_observed, a successful same-origin non-read response, matching control readback, and the page's save status is sufficient browser evidence. Do not activate unrelated controls, inspect hidden databases, or use shell/page scripts solely to obtain stronger private persistence proof. upload attaches files to an input[type=file] ref (or file_chooser=true with an observed attachment button ref) and is the ONLY way to do so — fill rejects file inputs. For a request such as 'keep scrolling until I stop you', use one scroll action with duration_seconds instead of spending repeated model rounds; cancelling/replacing the run stops it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes
tab_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.7/5.0
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: it discloses the two success return shapes (a fresh `page` vs `page_unchanged: true`), ref staleness/verification rules, that sequence stops before dispatch on ambiguity or failed guards, that upload is the only file path and fill rejects file inputs, and what counts as sufficient evidence for a save action. This is unusually complete behavioral disclosure.

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?

The core purpose is front-loaded, but the body is a dense wall of run-on prose mixing workflow guidance, evidence policy, and parameter semantics with little structure; several clauses (save-evidence proof, private-persistence warnings) could be tightened or moved. Length is partly justified by the large nested schema, but structure is weak.

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?

For a tool of this complexity with no output schema and many nested action variants, the description covers return values, verification, guard semantics, batching, uploads, and waiting behavior — everything an agent needs to invoke it correctly.

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?

The description explains the semantics of the hard parameters beyond a bare schema: kind/type alias handling, the exact-ref requirement, option+query for select, checked state, fill_form batching with depends_on, and expect_before/expect_after guards. It does not explain tab_id or the top-level container, and the reported schema coverage is low, so a 4 rather than 5.

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?

Opens with a specific verb+resource+scope ('Perform one verified action in a leased tab') and enumerates the exact action.kind values, so the agent knows precisely what the tool does. It also differentiates from siblings by referring to page/observe/extract results and browser_extract, so an agent can route correctly without opening other schemas.

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?

Gives rich when-to-use guidance: select for anything list-picking, check for any checked/selected state, sequence for short reversible multi-step flows (with an explicit 'do not place a consequential final submit in a sequence'), fill_form for stable fields, scroll+duration_seconds for continuous scrolling, until for late effects. It also states when NOT to act (no unrelated controls, no inspecting hidden databases, no shell scripts for stronger proof).

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

Deploy Server

Other Tools