Skip to main content
Glama

Save a session as a workflow

writ_browser_save
Destructive

Saves the open session as a replayable workflow and closes the browser, in the place its browser ran: the user's desktop library or Writ Cloud. Composed functions become callable API functions, declared inputs become its parameters. The answer carries the steps, the inputs and a run_example; the workflow runs at zero AI cost through writ_run_workflow. A save that references something no run could resolve is refused with the reasons, and the browser stays open.

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": {
      "session_id": "<session_id>"
    },
    "name": "writ_browser_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
listingNoIts Marketplace title, summary, tags, category and intent: people-facing, English, no build status.
save_toNo
keep_openNo
session_idYes
descriptionNo
allow_no_dataNoSave a workflow that returns no data, on purpose.
contribute_to_catalogNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / contribute_to_catalog
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / keep_open
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / listing
      Added value: +{
      +  "description": "Its Marketplace title, summary, tags, category and intent: people-facing, English, no build status.",
      +  "type": "object"
      +}
    • addedInput schema / properties / save_to
      Added value: +{
      +  "enum": [
      +    "desktop",
      +    "cloud",
      +    "both"
      +  ],
      +  "type": "string"
      +}
  2. Changed3 schema fields changed
    • changedInput schema / properties / allow_no_data / description
      Previous value: -"Saves a workflow that yields no data (navigation/actions only) on purpose. Off by default: a save with no data step and no defined function is refused for an API build (no define_function or extract yet) and warned for a task recording: such a workflow runs green and returns nothing."New value: +"Save a workflow that returns no data, on purpose."
    • removedInput schema / properties / keep_open
      Removed value: -{
      -  "description": "Leaves the browser open after saving (default false: saving closes it).",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / name / description
      Removed value: -"Short workflow name (defaults to the goal)."
  3. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations already flag destructive/openWorld/non-idempotent, and the description goes well past them: it discloses that the browser is closed on success, the exact target location of the save, the contents of the response (steps, inputs, run_example), and the failure semantics (a save referencing something no run could resolve is refused with reasons and the browser stays open). That is real behavioral context an agent cannot derive from the hints.

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?

Four sentences, front-loaded with the action and side effect, then return payload, then failure mode. Dense but every sentence carries information; no filler or restatement of the title.

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?

There is no output schema, so describing the response shape (steps, inputs, run_example) is necessary and done. For a destructive, open-world mutation it covers side effects and refusal behavior well; the remaining gap is parameter-level meaning for the majority of the inputs.

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 only 25% across 8 parameters, so the description needs to compensate and largely does not. 'In the place its browser ran: desktop library or Writ Cloud' gives partial meaning for save_to, and 'the browser stays open' on refusal hints at keep_open, but name, description, listing, allow_no_data and contribute_to_catalog are left entirely to the sparse schema.

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 object ('Saves the open session as a replayable workflow') plus its two consequences: the browser closes and the artifact lands where the browser ran (desktop library or Writ Cloud). This is clearly distinct from listing sessions (writ_browser_sessions) or updating a workflow (writ_update_workflow) without needing to name them.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: you save an open browser session once it is composed, and the result is later run via writ_run_workflow at zero AI cost. There is no explicit 'use this when / don't use this when' and no stated preconditions (e.g. session must still be live) beyond the refusal case.

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.