Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_browser_action

Destructive

Performs selector-based browser interactions such as clicking, filling, typing, pressing keys, checking, selecting, or hovering within an authorized session.

Instructions

Perform a selector-based browser action: click, fill, type, clear, press, check, uncheck, select, or hover.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "engagement_id": "<engagement_id>",
      "session_id": "<session_id>",
      "action": "<action>",
      "selector": "<selector>"
    },
    "name": "oc_browser_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
valueNo
actionYes
selectorYes
session_idYes
timeout_msNo
engagement_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already disclose the full risk profile (readOnlyHint=false, destructiveHint=true, openWorldHint=true, idempotentHint=false), so the description's burden is lower and it does not contradict them. However, it adds no behavioral context of its own: it never warns that fill/clear overwrite existing field content, that actions may fail or hang until timeout_ms elapses, or that the page state changes persist for the session.

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?

One sentence, front-loaded with the verb and resource, with the action list acting as a compact taxonomy. Nothing is padded, though the enumeration forms a long tail that could have been paired with a brief note on which actions require 'value'.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, open-world, 6-parameter mutation tool at 0% schema coverage, the description is thin. An output schema exists so return values need not be explained, but the missing prerequisite handling, the value-vs-action pairing, timeout behavior, and failure modes leave real gaps an agent would hit on first use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 6 parameters, so the description must compensate and largely does not. The enumerated actions do implicitly define valid values for the 'action' parameter (useful since the schema declares it as a bare string with no enum), but 'value', 'timeout_ms', 'session_id', and 'engagement_id' get no explanation at all, leaving it unclear which actions consume 'value'.

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?

The description uses a specific verb ('Perform') with a named resource ('selector-based browser action') and enumerates the concrete action set (click, fill, type, clear, press, check, uncheck, select, hover), so an agent knows exactly what class of operation this is. It stops short of differentiating itself from siblings like oc_browser_evaluate or oc_browser_set_state, which also manipulate page state.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no exclusions, and no guidance pointing to alternatives such as oc_browser_evaluate for JS execution or oc_browser_snapshot for reading the DOM. It also omits the prerequisite that a session_id from oc_browser_create/oc_browser_navigate must already exist, which is critical for correct invocation.

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