Skip to main content
Glama

batch_actions

Destructive

Run browser actions and form-filling steps in order, including navigation and extraction for multi-page reading; stop on submit-guard blocks and optionally return a post-run snapshot.

Instructions

Run actions or smart_fill_form steps in order, including navigate/extract for multi-page reading. Stops on Submit guard blocks; optional post-batch snapshot.

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": {
      "steps": "<steps>"
    },
    "name": "batch_actions"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYesact_fast or smart_fill_form steps (incl. reload/back/forward); also {action:"navigate",url} (GET only), {action:"extract",format:"text"|"markdown",selector?,maxChars?}, {action:"collect",selector,scrolls?:5,waitMs?:400,maxItems?:100,maxChars?:8000,fields?:["text","href","id"],textSelector?} (scroll, read matching elements each time, dedupe: virtualized feeds).
tabIdNo
expectNoSubmit evidence to wait for; returns submitVerified.
allowSubmitNo
snapshotModeNo
snapshotQueryNo
submissionKeyNoIdempotency key; repeat submits are refused.
allowDuplicateNo
returnSnapshotNo
continueOnErrorNo
observeAftermathNoObserve click aftermath for each action (adds up to 800 ms per click).
snapshotMaxCharsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.6.1
    • addedInput schema / properties / allowDuplicate
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / expect
      Added value: +{
      +  "description": "Submit evidence to wait for; returns submitVerified.",
      +  "properties": {
      +    "selector": {
      +      "type": "string"
      +    },
      +    "textMatches": {
      +      "type": "string"
      +    },
      +    "textNew": {
      +      "description": "Like textMatches, only text new since the click.",
      +      "type": "string"
      +    },
      +    "timeoutMs": {
      +      "type": "integer"
      +    },
      +    "urlMatches": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / observeAftermath
      Added value: +{
      +  "description": "Observe click aftermath for each action (adds up to 800 ms per click).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / snapshotQuery
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / steps / description
      Added value: +"act_fast or smart_fill_form steps (incl. reload/back/forward); also {action:\"navigate\",url} (GET only), {action:\"extract\",format:\"text\"|\"markdown\",selector?,maxChars?}, {action:\"collect\",selector,scrolls?:5,waitMs?:400,maxItems?:100,maxChars?:8000,fields?:[\"text\",\"href\",\"id\"],textSelector?} (scroll, read matching elements each time, dedupe: virtualized feeds)."
    • addedInput schema / properties / submissionKey
      Added value: +{
      +  "description": "Idempotency key; repeat submits are refused.",
      +  "type": "string"
      +}
  2. First observedv0.4.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is carried by structured data. The description adds one genuine behavior beyond that – it stops on Submit guard blocks and can optionally take a post-batch snapshot – but says nothing about failure/partial-execution semantics under default continueOnError=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?

Two dense sentences, front-loaded with the core action and followed by the most consequential behavioral note. No filler, though one clause ('including navigate/extract for multi-page reading') partly duplicates the steps schema.

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 12-parameter, destructive, open-world batch executor with no output schema, the description omits too much: how errors are surfaced, what submitVerified means in practice, how idempotency keys interact with retries, and what the snapshot returns. It is under-specified relative to the tool's complexity.

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 coverage is only 33% across 12 parameters, so the description is expected to compensate and does not. It names only the navigate/extract capability and the optional snapshot; submit gating (allowSubmit, expect, submissionKey, allowDuplicate), snapshotMode/snapshotQuery, observeAftermath and error handling are left entirely to sparse schema text.

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 and resource ('Run actions or smart_fill_form steps in order') plus a scope qualifier ('including navigate/extract for multi-page reading'), which distinguishes it from the single-action act_fast and the form-only smart_fill_form. It stops short of explicitly contrasting with tabs_batch or capture_page.

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 by 'in order' and 'multi-page reading' – i.e. use when several actions must run sequentially in one call. However, it never says when to prefer act_fast or tabs_batch instead, nor any precondition for batching.

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