Skip to main content
Glama

Create Stream

create_stream

[Act · writes · schedules paid runs] Create a new research stream (external profile, company, topic, person interests, hiring signals, or ad watch). Running the stream on its schedule costs credits (see get_cost_estimate for the per-type cost). own_profile streams are not created here — they come from subscription checkout.

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": {
      "type": "<type>",
      "name": "<name>"
    },
    "name": "create_stream"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesUser-facing label for this stream
typeYesStream type
paramsNoType-specific config: topic uses {query, authorsIndustryId?, contentType?, postedLimit?, sortBy?}; hiring_signals/ad_watch use {company?, keywords?, ...}
scheduleNoRun schedule. Defaults to 'weekly'. 'monthly' runs every 30 days — the cheapest recurring cadence, and the usual choice for client profiles reported on monthly.
source_urlNoLinkedIn URL for external_profile / company / person_interests streams
history_daysNoHow far back the first run should reach, in days. Bounds the walk by TIME where initial_max_pages bounds it by COST — the run stops at whichever limit it hits first, so pair a window with enough pages to reach it. Honoured for external_profile, company and person_interests; the search types ignore it. Applies to this pull alone and is never saved on the stream, so scheduled runs keep topping up from where the last one stopped rather than re-fetching the window.
initial_max_pagesNoOpt-in deep first-run for external_profile, company and person_interests streams (1-5, default 1). A budget, not a price — you are billed for pages actually walked. A page is ~50 posts for profile/company feeds and ~100 engagement events for person_interests. Other stream types ignore this. Later scheduled runs pull one page in the steady state; a person_interests stream may walk further to close a gap after a missed tick, and is billed only for what it walks.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare writes (readOnlyHint=false), openWorldHint=true and non-idempotent, so the core safety profile is covered. The description adds valuable non-schema behavior: scheduled runs consume credits and history_days is a one-shot pull never persisted on the stream. It still doesn't state auth requirements or what a successful call returns, so it's additive but not rich.

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?

The bracketed prefix ('Act · writes · schedules paid runs') front-loads the key traits, and the two following sentences carry non-redundant constraints. Slightly dense but every clause does work.

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 7-parameter, nested-object mutation with no output schema, the description covers the cost model, the own_profile exclusion, and the ephemeral nature of first-run bounds. The main remaining gap is the return value and any permission prerequisites, but the structured schema absorbs most of the detail burden.

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 description coverage is 100%, so every parameter (including the nested params object and its per-type keys) is already documented in the schema. The description adds only indirect context via the credit-cost pointer, not parameter-level meaning beyond the schema, making the baseline 3 appropriate.

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?

Specific verb+resource ('Create a new research stream') with the enumerated stream types, and it explicitly carves out the own_profile case to a different path. An agent can distinguish this from create_campaign/create_collection without opening the schema.

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

Usage Guidelines4/5

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

Gives clear use conditions and points to get_cost_estimate for per-type cost, plus the exclusion that own_profile streams come from subscription checkout. It does not explicitly contrast against sibling creation tools like create_campaign or create_collection, so it stops short of full alternative routing.

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