Skip to main content
Glama
Brave Session MCP

Brave Session MCP

by MacStenk

brave_fill

Destructive

Fills a visible input field in a specific browser tab via its tab-bound element reference to enter form text in an existing session.

Instructions

Füllt ein sichtbares Eingabefeld anhand seiner tabgebundenen Referenz.

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": {
      "tabId": "<tabId>",
      "ref": "<ref>",
      "text": "<text>"
    },
    "name": "brave_fill"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYesElementreferenz aus brave_read für genau diesen Tab.
textYes
tabIdYesStabile Tab-ID aus brave_tabs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the mutation/world-affecting profile is carried by structured data. The description adds one genuinely new behavioral constraint — the field must be visible — but does not explain the destructive flag: whether existing text is replaced or appended, or whether the fill is editable/reversible afterwards. No annotation contradiction: 'füllt' (writes) is consistent with readOnlyHint=false.

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?

A single short sentence with zero filler, front-loading the action and its object. It is efficient but arguably under-specified rather than optimally concise; one more clause on replacement vs. append would have earned its place.

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?

For a 3-required-parameter browser-mutation tool with no output schema, the definition omits whether the call returns anything (e.g. confirmation or updated element state) and how it interacts with existing field content. The annotations carry the safety profile, which limits but does not eliminate the gap. Also worth noting: the description is in German while the tool and sibling names are English.

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 coverage is 67%: 'ref' and 'tabId' are documented in the schema, while 'text' (maxLength 100000) has no schema description. The description reinforces that the ref is tab-bound ('tabgebundene Referenz') and adds that the target must be a visible input field, but says nothing about what 'text' means for the field's existing content. Baseline 3 is appropriate at this coverage level.

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?

States a specific verb+resource: 'Füllt ein sichtbares Eingabefeld' (fills a visible input field), scoped by 'anhand seiner tabgebundenen Referenz'. An agent can distinguish this from brave_click or brave_read because the target is explicitly an input field and the operation is text insertion. It stops short of naming a sibling to route away from.

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?

No when-to-use or when-not-to-use guidance is given; the only indirect signal is 'sichtbares' (visible), which hints that hidden/offscreen fields are out of scope. There is no mention of what to do first (e.g. brave_read for the ref), of alternatives, or of cases where clicking/uploading is the right tool instead.

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