Skip to main content
Glama

Press keys

well_browser_key
Destructive

Press a key ("Tab"), a chord ("ctrl+a") or a sequence ("Tab Tab"), repeat times (1 to 100). Enter, Return and Space are refused: to submit or press a control, click it by ref. It acts in the Well tab group of the caller's own Chrome, picked with well_select_browser (or the only one connected). Refs come from well_browser_read_page or well_browser_find and go stale when the page changes: read again then.

Input Schema

NameRequiredDescriptionDefault
textYes
repeatNo
tab_idNoThe tab, as tabs_context lists it (tab-N). Default: the active tab of the Well group.
workspace_idNoTarget workspace. Omit when the token authorizes one workspace. Required when it authorizes several — a write lands in exactly one workspace and this call would not say which.
conversation_idNoThe conversation id returned by the previous Well result, in its meta under well/conversation_id, in its structuredContent, or in its JSON text block. Pass it back on every call in the same conversation, including a call a card makes, so the chosen workspace and the earlier answers still apply. It decides the conversation on its own: nothing the host states about the session replaces it. Omit it only on the first call of a conversation.
idempotency_keyNoOptional client-supplied key. A retried write with the same key returns the original result instead of re-applying the operation.
workspace_scopeNoRestrict this call to the family: the token's primary workspace plus the company workspaces under it that you are a member of. Unrelated authorized workspaces drop out of the read; row reads merge across the family, while a per-workspace figure still reports exactly one workspace.

Output Schema

NameRequiredDescriptionDefault
tabsNo
textNo
errorNo
notesNo
statusNo
successYes
state_changesNo
conversation_idNoThe conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.
newly_connectedNoTools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. The connected-line rule says when to tell an entry; when it does, one line per entry, in the person's language: "<name> is connected.". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later.
conversation_id_noteNoPresent only when the server opened a fresh lane, stating that no choice recorded earlier was read.
conversation_id_sourceNoWhere the conversation id came from: the host's own request meta, the caller's argument, or a fresh lane the server opened.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "conversation_id": {
      +      "description": "The conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.",
      +      "type": "string"
      +    },
      +    "conversation_id_note": {
      +      "description": "Present only when the server opened a fresh lane, stating that no choice recorded earlier was read.",
      +      "type": "string"
      +    },
      +    "conversation_id_source": {
      +      "description": "Where the conversation id came from: the host's own request meta, the caller's argument, or a fresh lane the server opened.",
      +      "enum": [
      +        "host_meta",
      +        "argument",
      +        "minted"
      +      ],
      +      "type": "string"
      +    },
      +    "error": {
      +      "type": "string"
      +    },
      +    "newly_connected": {
      +      "description": "Tools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. The connected-line rule says when to tell an entry; when it does, one line per entry, in the person's language: \"<name> is connected.\". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later.",
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "name": {
      +            "type": "string"
      +          },
      +          "service_id": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "name",
      +          "service_id"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "notes": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "state_changes": {
      +      "items": {
      +        "oneOf": [
      +          {
      +            "additionalProperties": false,
      +            "properties": {
      +              "tab_id": {
      +                "maxLength": 4096,
      +                "minLength": 1,
      +                "type": "string"
      +              },
      +              "type": {
      +                "const": "tab_opened",
      +                "type": "string"
      +              }
      +            },
      +            "required": [
      +              "type",
      +              "tab_id"
      +            ],
      +            "type": "object"
      +          },
      +          {
      +            "additionalProperties": false,
      +            "properties": {
      +              "download_id": {
      +                "minLength": 1,
      +                "type": "string"
      +              },
      +              "type": {
      +                "const": "download_started",
      +                "type": "string"
      +              },
      +              "url": {
      +                "maxLength": 4096,
      +                "type": "string"
      +              }
      +            },
      +            "required": [
      +              "type",
      +              "download_id",
      +              "url"
      +            ],
      +            "type": "object"
      +          },
      +          {
      +            "additionalProperties": false,
      +            "properties": {
      +              "download_id": {
      +                "minLength": 1,
      +                "type": "string"
      +              },
      +              "path": {
      +                "maxLength": 4096,
      +                "type": "string"
      +              },
      +              "size_bytes": {
      +                "maximum": 9007199254740991,
      +                "minimum": 0,
      +                "type": "integer"
      +              },
      +              "type": {
      +                "const": "download_completed",
      +                "type": "string"
      +              },
      +              "url": {
      +                "maxLength": 4096,
      +                "type": "string"
      +              }
      +            },
      +            "required": [
      +              "type",
      +              "download_id",
      +              "url"
      +            ],
      +            "type": "object"
      +          },
      +          {
      +            "additionalProperties": false,
      +            "properties": {
      +              "download_id": {
      +                "minLength": 1,
      +                "type": "string"
      +              },
      +              "error": {
      +                "maxLength": 4096,
      +                "type": "string"
      +              },
      +              "type": {
      +                "const": "download_failed",
      +                "type": "string"
      +              },
      +              "url": {
      +                "maxLength": 4096,
      +                "type": "string"
      +              }
      +            },
      +            "required": [
      +              "type",
      +              "download_id",
      +              "url"
      +            ],
      +            "type": "object"
      +          }
      +        ]
      +      },
      +      "type": "array"
      +    },
      +    "status": {
      +      "enum": [
      +        "ok",
      +        "failed"
      +      ],
      +      "type": "string"
      +    },
      +    "success": {
      +      "type": "boolean"
      +    },
      +    "tabs": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "active": {
      +            "type": "boolean"
      +          },
      +          "tab_id": {
      +            "minLength": 1,
      +            "type": "string"
      +          },
      +          "title": {
      +            "maxLength": 4096,
      +            "type": "string"
      +          },
      +          "url": {
      +            "maxLength": 4096,
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "tab_id",
      +          "title",
      +          "url"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "text": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "success"
      +  ],
      +  "type": "object"
      +}
  2. Added

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety profile is covered. The description usefully adds the execution environment (Well tab group of the caller's own Chrome, resolved via well_select_browser or the sole connection) and the staleness hazard, but never explains why the call is destructive or what state it can alter on the page.

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?

Front-loads the accepted input formats and bounds in the opening sentence, then the exclusions and environment. Slightly overpacked, and the closing remark about refs going stale does not map to any parameter on this tool, so it is marginally wasted.

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

Completeness4/5

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 not be described. For a destructive browser-input tool the description covers environment, workspace scoping context, and retry semantics via the annotated idempotency_key, leaving only the nature of the destructive effect unexplained.

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 71% and most optional parameters carry their own descriptions, yet the key parameter 'text' has no schema description at all — the description supplies its full syntax (key name, chord, space-separated sequence) and the repeat range, which is real added meaning. The trailing sentence about refs, however, refers to a parameter this tool does not expose.

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 concrete verb and resource (press key/chord/sequence) with literal examples like "ctrl+a" and "Tab Tab", plus the repeat bound. An agent can distinguish this from well_browser_type and well_browser_left_click purely from the description.

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?

Explicitly names the excluded inputs (Enter, Return, Space) and routes them to the alternative action (click by ref), and states that stale refs require a fresh read before acting. That is a clear when-to-use / when-not-to-use rule set.

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.

Resources