Skip to main content
Glama

Heista

by co.heista

Call Creative Agent

call_creative_agent_preset

Invoke a Creative Agent (character) preset. Every preset is a purpose-built character the workspace has authored or the Heista catalog has published — copy voice, art direction, strategy, creative direction, etc. ONE-SHOT: give the character a message, get its response back as text.

Discover callable presets via list_creative_agent_presets. Workspace-authored presets are only callable inside their owning org; official templates (visibility=public_template) are callable from any authenticated org.

INPUTS: agent_id (UUID from list_creative_agent_presets), message (the turn text), optional brand_id (server-loads multi-strategy brand summary for character context), optional working_context (light labels the character reads as IN SCOPE — pinned brand + strategies + documents + playbook), optional thread_id (continuity id), optional idempotency_key (5-minute retry safety).

Returns the character's response as plain text plus a structured envelope with usage, model, provider, thread_id. Metered — cost depends on character model + context size, typically 2-10 credits per turn. Charged after success on real token usage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageYesThe user turn — the message the caller wants the character to respond to. One-shot; not persisted as a conversation history unless the caller supplies thread_id continuity.
agent_idYesThe Creative Agent preset id to call. Discover ids via list_creative_agent_presets. Workspace-authored agents are only callable from within the owning org; official templates (visibility=public_template) are callable from any org.
brand_idNoOptional Heista brand id (a.k.a. brief id). When provided, the runtime server-loads the multi-strategy brand summary via `loadMultiBrandContext` and injects it into the agent's system prompt as BRAND INTELLIGENCE. RLS-scoped read — a brand outside the caller's workspace resolves to no summary (silent fall-through).
thread_idNoOptional continuity id round-tripped on the response. Callers manage their own thread state — the runtime does NOT persist history for library calls (chat surface uses its own session table).
idempotency_keyNoOptional unique key to make this call safely retryable. If the same key + org repeats within 5 minutes, the cached response returns without re-charging.
working_contextNoOptional Working Context labels — brand pin, pinned strategies, pinned documents, loaded playbook. Rendered into the agent's system prompt as an IN SCOPE bullet block so the agent knows what the workspace has pinned. IDs must reference workspace-owned rows. For deeper brand intelligence, pass `brand_id` (server-resolved).

TDQS

A4.3/5.0
Behavior4/5

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

Beyond annotation defaults, the description reveals cost behavior (2-10 credits), idempotency key retry safety, and that history is not persisted unless thread_id is provided. It does not contradict annotations.

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 description is well-structured, starting with purpose, then discovery, inputs, and output/cost. It is moderately lengthy but each sentence adds value. Minor redundancy could be trimmed, but overall efficient.

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?

Given the tool's complexity (6 parameters, nested objects, no output schema), the description covers essential aspects: one-shot operation, org restrictions, optional inputs, cost, and return envelope structure. Missing explicit details on response format, but acceptable without output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the input schema already describes all parameters, the description adds high-level context for each (e.g., brand_id loads brand summary, working_context as labels, idempotency_key for retries). This extra guidance aids correct usage beyond the schema alone.

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?

The description clearly states the tool invokes a Creative Agent preset, a purpose-built character. It specifies the one-shot nature (message in, text out) and distinguishes from siblings by referencing list_creative_agent_presets for discovery and noting org constraints.

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?

The description explains when to use the tool (to call a creative character) and provides context on org-based accessibility (workspace vs public). However, it lacks explicit instructions on when not to use it or comparison to alternatives like dispatch tools.

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

All Heista toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

Despite the high tool count, most tools have distinct purposes with thorough descriptions that specify when to use each. Some overlap exists among creative direction tools (call_creative_worlds vs chat_with_creative_worlds), but the descriptions clarify usage patterns.

Naming Consistency3/5

Naming conventions are inconsistent overall: some follow verb_noun (create_powersource_url, decode_ad), others use noun_verb or compound names (adformula_intelligence, fleet_analytics_overview). However, subgroups like dispatch_* and list_*_presets maintain internal consistency.

Tool Count2/5

112 tools is far beyond the typical 3-15 range for well-scoped servers. While the server covers a broad domain, the sheer number likely overwhelms agents and suggests insufficient consolidation of related operations.

Completeness4/5

The tool set covers core creative intelligence workflows: brand analysis, ad decoding, script generation, creative direction, and research. Minor gaps exist (e.g., no social media publishing tools), but the main use cases are well-supported.

Resources