Skip to main content
Glama

Browser Fill

browser_fill

Fills a single browser input field by CSS selector in an SAP GUI session. Use it to enter a value into one specific field; to set multiple fields on the same screen, use sap_fill_form instead.

Instructions

Fill a single input field by CSS selector. For filling multiple fields on the same screen, use sap_fill_form instead - it fills all fields in a single call, which is much faster.

Session parameter:

  • session=None (default): Uses primary session ("s1")

  • session="s2": Targets specific session (for parallel agents)

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": {
      "selector": "<selector>",
      "value": "<value>"
    },
    "name": "browser_fill"
  }
}

Input Schema

NameRequiredDescriptionDefault
valueYesValue to fill in the field.
sessionNoSession ID (e.g., "s1", "s2"). None uses primary session.
agent_idNoAgent identifier for binding check. Optional.
selectorYesCSS selector of the input field.

Output Schema

NameRequiredDescriptionDefault
errorNoError message if success=False
popupNoPresent when a popup dialog is active on screen
valueYesValue that was entered
successNoWhether the operation succeeded
selectorYesSelector that was filled
active_windowNoWhich window was operated on (e.g., 'wnd[0]', 'wnd[1]'). If 'wnd[1]' or higher, a modal dialog is open.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full disclosure burden, yet it says nothing beyond the mechanical action. It does not state whether existing field content is cleared or appended, whether change/blur events fire, whether it waits for the element to be interactable, or what happens when the selector matches nothing.

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?

The core action and the sibling alternative are front-loaded in the first two sentences with no wasted words. The trailing session block is slightly redundant with the schema, costing a point, but it is clearly formatted and short.

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

Completeness3/5

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

An output schema exists, so return values need no explanation, and the routing guidance is complete. However, for a state-changing UI interaction with zero annotation coverage, the absence of any note on element-waiting, event triggering, or failure modes leaves a real gap for correct invocation.

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 all four parameters are already documented in the schema, including session and agent_id. The description's session bullet largely restates the schema's "Session ID (e.g., \"s1\", \"s2\"). None uses primary session." The one genuine addition is the parallel-agent rationale for targeting a non-default session.

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 and resource ("Fill a single input field") plus the addressing mechanism ("by CSS selector"), and explicitly narrows scope to one field, which distinguishes it from the form-level sibling. An agent can identify this tool without opening the schema.

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 an explicit alternative with a stated condition: for multiple fields on the same screen, use sap_fill_form, with the reason ("fills all fields in a single call, which is much faster"). The single-field case is defined by contrast, leaving no routing ambiguity.

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