Skip to main content
Glama

Pause, resume, stop or answer a search

control_search

A started search: pause, resume, stop (the leads found are kept and charged), or continue — the answer to a search that asks about a higher price (status asking): it SPENDS the extra credits of get_search's ask.continue_credits; show them and pass them as confirm_credits after the user's yes. [REST: POST /api/tasks/{id}/control]

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": {
      "task_id": "<task_id>",
      "action": "<action>"
    },
    "name": "control_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
task_idYesThe search id (task id), e.g. from list_searches or create_search.
confirm_creditsNoThe price in credits the matching quote returned, shown to the user and confirmed by them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Adds behavior beyond the annotations: stopping keeps the leads found and charges for them, and 'continue' spends extra credits. That cost/irreversibility context is exactly what an agent needs and is not derivable from the annotation flags. It still does not say what the response looks like or whether paused searches expire, and the cost-bearing stop is only loosely reconciled with destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is compact, but it is a single run-on sentence with stacked parentheses and a bracketed REST note, which forces the agent to parse several clauses to find the key cost warnings. Front-loading the operation list is good; the credit-spending warning would be stronger as its own sentence.

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?

For a 3-parameter control tool with no output schema, the definition covers the action set, the credit-cost implications, the confirmation requirement, and the backing endpoint. The remaining gap is the lack of a clear boundary against the continue_search sibling and no indication of what state the search ends in after each action.

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%, and the description adds real meaning for confirm_credits by tying it to get_search's ask.continue_credits and the user-confirmation flow. The action enum and task_id are already documented in the schema, so the added value is concentrated in one parameter.

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?

Names the resource (a started search) and enumerates the four concrete operations (pause, resume, stop, continue), and it disambiguates 'continue' as the answer to a price-question search in 'asking' status rather than a plain resume. It is written as a sentence fragment with heavy parenthetical nesting, and it never distinguishes the 'continue' action from the sibling tool continue_search, which could confuse selection.

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?

Gives useful conditional guidance for one branch: use 'continue' only when the search status is 'asking', show the credits, and pass them as confirm_credits after the user says yes. It offers no guidance on choosing among pause/resume/stop, no prerequisites for stopping, and no statement about when to prefer this over continue_search or run_search.

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