Skip to main content
Glama

FlowCastle

by ai.flowcastle

send_flow_to_contacts

Run an EXISTING interactive flow for each listed contact right now, outside any trigger — as if each of them had just triggered it. Use it when the WHOLE message is the flow — its first block's text, media and buttons are what the recipient sees. To send your own custom text with buttons that run a flow on tap, prefer send_message with buttons: [{ text, flowId }]; it needs no wrapper flow. The flow starts at its start block for every recipient, and any {{var|name}} inside it resolves against that recipient's own variable context. No deploy is needed — the runtime compiles the flow on demand — but the flow must already be applied (use the ids apply_actions returned). Contacts are targeted by contactId only (from list_contacts), 1 to 50 per call. Duplicates are collapsed. Each contact is dispatched independently: one bad id fails its own row in results and the others still go out, so read sent/failed, not just the absence of an error. BROADCAST and OPERATION flows are rejected — a broadcast flow runs in an audience scope (send it with its broadcast) and an operation runs in system context (use run_operation). For a large audience this is the WRONG tool: create a broadcast whose flow filter selects the audience, and launch that once. Requires the send_flow_to_contact permission. NOT idempotent and not reversible — every call reaches real people again and a sent message cannot be recalled. Confirm the flow and the exact recipient list with the user before calling, and never retry a timed-out call blindly.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
flowIdYesRequired. Id of the already-applied INTERACTIVE flow to run. Broadcast and operation flows are rejected.
contactIdsYesRequired. Between 1 and 50 FlowCastle contact ids (from list_contacts) — NOT platform ids. Each one receives its own run of the flow.
applicationIdNoApplication (workspace) id. Optional: an application-scoped key (app_...) defaults to its own application, but a personal key (usr_...) has no default and omitting it fails with MCP_APPLICATION_REQUIRED. Call list_applications to get the id.

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description adds critical behavioral context: no deploy needed, duplicates collapsed, each contact dispatched independently, failed ids fail only their own row with `sent`/`failed`, permission requirement, and that calls are NOT idempotent, NOT reversible, and cannot be retried blindly. There is no contradiction with annotations.

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

Conciseness5/5

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

The description is long but unusually dense and decision-oriented: every sentence earns its place, covering exact semantics, exclusions, permissions, failure behavior, and non-idempotency. It is front-loaded with the core behavior and then builds outward to alternatives and caveats. No filler or redundancy is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a high-stakes, non-idempotent tool with no output schema, the description is remarkably complete: it covers preconditions (flow must be applied, use ids from apply_actions), input constraints (1-50 contacts), result semantics (`sent`/`failed` rows), permission requirements, irreversible side effects, and correct alternatives for other scenarios. An agent has everything needed to invoke it safely and correctly.

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?

Schema coverage is 100%, so the params are already documented. The description still adds meaning beyond the schema: contacts must be FlowCastle contact ids from list_contacts (not platform ids), each recipient gets its own run, `{{var|name}}` resolves against the recipient's variable context, the flow starts at its start block, and applicationId has defaulting behavior described. That goes beyond the schema's field descriptions.

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 leads with a precise verb and resource: 'Run an EXISTING interactive flow for each listed contact right now, outside any trigger'. It states the visible effect—'the first block's text, media and buttons are what the recipient sees'—and explicitly distinguishes this from sending custom text with a button via send_message. This is specific and easily differentiated from sibling tools.

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

Usage Guidelines5/5

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

The description gives explicit when-to-use vs alternatives: use it when the WHOLE message is the flow, and prefer send_message with `buttons: [{ text, flowId }]` for custom text. It also flags exclusions: BROADCAST and OPERATION flows are rejected, and for a large audience it says this is the WRONG tool and directs the agent to create a broadcast instead.

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

All FlowCastle 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

A4.1/5.0
Disambiguation4/5

Each get_/list_ tool targets a distinct resource and the descriptions carefully separate similar pairs like get_application_context vs get_workspace_summary and get_broadcast_details vs get_broadcast_analytics. The main ambiguity is apply_actions vs validate_actions, since one runs the other's validation, but the descriptions make that relationship explicit.

Naming Consistency4/5

Names consistently follow verb_object snake_case and use familiar verbs like create, get, list, and update. Minor deviations such as read_messages instead of list_messages, apply_actions/validate_actions with plural nouns, and run_flow_autotest are still predictable and readable.

Tool Count2/5

33 tools exceeds the 25-tool threshold and makes the surface feel heavy, even though the domain is broad. Many of the read-only getters are individually useful but could be consolidated, such as merging module catalog/details or workspace/application context.

Completeness4/5

Core workflows are covered: application lifecycle, flow editing through apply_actions, deployment, contacts, broadcasts, modules, and message/event reads. Minor gaps exist, such as no dedicated delete for contacts, applications, or broadcasts, and no rollback for deployments, but agents can work around or avoid these.

Resources