Skip to main content
Glama

Build an HTTP extraction

writ_create_http_extraction
Destructive

Drafts or revises a multi-request browserless HTTP extraction (loops, GraphQL, cursor pagination) from captured requests and a plain-language goal. Every option: writ_help('writ_create_http_extraction').

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": {
      "goal": "<goal>"
    },
    "name": "writ_create_http_extraction"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYes
applyNofalse (default) drafts; true writes.
workflowNo
step_indexNo
workflow_idNo
requirementsNo
desired_inputsNo
request_samplesNo
response_sampleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / desired_inputs
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / request_samples
      Added value: +{
      +  "items": {
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / requirements
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / response_sample
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / step_index
      Added value: +{
      +  "type": "integer"
      +}
    • addedInput schema / properties / workflow
      Added value: +{
      +  "type": "string"
      +}
  2. Changed8 schema fields changed
    • changedInput schema / properties / apply / description
      Previous value: -"false (default) returns a reviewable draft; true writes a valid draft to the workflow."New value: +"false (default) drafts; true writes."
    • removedInput schema / properties / desired_inputs
      Removed value: -{
      -  "description": "Caller parameters such as query, min_price, max_price, limit and cursor.",
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • removedInput schema / properties / goal / description
      Removed value: -"Exact inputs, output fields, filters, ordering and pagination behavior wanted."
    • removedInput schema / properties / request_samples
      Removed value: -{
      -  "description": "Relevant calls returned by writ_browser_network/capture_network, including representative response bodies when available.",
      -  "items": {
      -    "type": "object"
      -  },
      -  "type": "array"
      -}
    • removedInput schema / properties / requirements
      Removed value: -{
      -  "description": "Extra mapping, dedupe, filtering or cursor requirements.",
      -  "type": "string"
      -}
    • removedInput schema / properties / response_sample
      Removed value: -{
      -  "description": "Optional representative JSON/HTML response when it is not in request_samples.",
      -  "type": "string"
      -}
    • removedInput schema / properties / step_index
      Removed value: -{
      -  "description": "api_call step to replace; defaults to the first, or appends one.",
      -  "type": "integer"
      -}
    • removedInput schema / properties / workflow
      Removed value: -{
      -  "description": "Existing workflow name (or workflow_id).",
      -  "type": "string"
      -}
  3. First observed

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, non-idempotent and non-read-only, so the safety profile is largely covered. The description adds that the default is a draft and that the target is a live multi-request flow built from captured traffic, which is useful. It never tells the agent what an applied run actually writes or destroys, despite destructiveHint=true, which is the key behavioral gap.

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 sentences, front-loaded with the core action and capability scope; the trailing pointer to writ_help is compact and unambiguous. No filler, though it spends a sentence on a documentation redirect rather than on the missing parameter semantics.

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 destructive, open-world tool with nine inputs and no output schema, the definition is materially incomplete: most parameters are unexplained, revision flow (workflow_id/step_index) is undocumented, and the consequences of apply=true are unstated.

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?

Only the apply parameter is described in the schema (11% coverage), and the description only maps two of the nine inputs: goal and request_samples. Seven parameters, including workflow, workflow_id, step_index, requirements, desired_inputs, and response_sample, are explained nowhere, so the description does not compensate for the coverage gap.

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 pair ("drafts or revises") and a precise resource: a multi-request, browserless HTTP extraction with named capability markers (loops, GraphQL, cursor pagination). "Browserless" implicitly separates it from the writ_browser_* family and from writ_crawl_site, but no sibling is named explicitly, so it falls short of a 5.

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?

"Drafts or revises" implies the creation/update context, and the requirement of captured requests plus a goal implies a prerequisite. There is no explicit when-to-use versus writ_create_automation, writ_crawl_site, or writ_create_monitor, and no when-not guidance; the fallback referral to writ_help only delegates rather than guides.

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.