Skip to main content
Glama

TaScan

by io.github.snowbikemike
OverviewDiscussionsAdmin

tascan_create_fanout

Create a fan-out: 1-30 seats (RESEARCH by default, or LOCAL subagent seats) plus one synthesizer under ONE cycle root (POST /coord/fanouts). No Decision cards, Parked cards or pages per seat: only a control action or the closing roll-up reaches a human. Needs an API key with agent:dispatch:code (an admin session has no dispatch budget: key_required). dry_run true runs the same validation and ceiling/cap pre-check and returns dry_run, plan_sha256, seats and problems without spending budget or creating anything. Otherwise it consumes seats + 1 dispatch units BEFORE the create; a refusal only the database can see (cap_below_plan, fanout_open_limit, bad agent_id, reserve_floor_unset) still consumes them, by design. Fails fanout_ceiling_unset until the owner sets a ceiling, over_ceiling when cap exceeds it. idempotency_key replays a duplicate within 24h on the same plan, else idempotency_body_mismatch. Every seat, the synth and the roll-up leave a signed completion. Track with tascan_get_fanout.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
capYesThis fan-out's total micro-USD budget, synth reserve included. Refused over_ceiling if it exceeds the org's fan-out spending ceiling.
seatsYes1-30 seats. Each names the agent that runs it; brief/role fall back to seat_defaults when omitted.
synthYesThe synthesizer that runs once the barrier closes, reading every done seat's stored output as DATA.
titleYesShort human title (1-200 chars). T_F becomes "FANOUT: <title>"; seats become "RESEARCH: [seat-NN] <title>"; the synth becomes "RESEARCH: [synth] <title>".
canaryNoHow many seats release immediately; the rest stay held on T_F until the first canary settles done. Default min(2, seats.length).
min_okNoMinimum seats that must finish done before the synth barrier can close. Default ceil(seats.length / 2).
dry_runNotrue runs the same validation plus the ceiling/cap pre-check and returns {dry_run:true, plan_sha256, seats, problems:[]} WITHOUT consuming budget or creating a fan-out -- a real preflight, not a real create.
breaker_kNoPaid (non-infrastructure) seat failures before the breaker pauses the fan-out (2-5, default 2). An expired run never counts.
project_idYesWorking project (UUID). The fan-out root T_F is minted on its Questions list (coord_ensure_lists).
seat_reviewNoper_seat mints one review per seat (allowed for at most 10 seats); none skips seat review. Default per_seat for <=10 seats, none above that.
deadline_minNoMinutes before an idle seat is dropped and the barrier re-evaluated, and before a stuck synthesizing fan-out closes deadline (10-1440, default 240).
seat_defaultsNoShared defaults applied when a seat names no brief of its own.
idempotency_keyNoOptional replay key (<= 200 chars). The same key within 24h on the same plan returns duplicate:true with the existing fanout_id; on a different plan it is refused idempotency_body_mismatch.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / dry_run / description
      Previous value: -"Forwarded to POST /coord/fanouts as given. The route has no server-side preflight for this path today, so true still performs a REAL create -- do not rely on it to avoid creating a fan-out."New value: +"true runs the same validation plus the ceiling/cap pre-check and returns {dry_run:true, plan_sha256, seats, problems:[]} WITHOUT consuming budget or creating a fan-out -- a real preflight, not a real create."
    • addedInput schema / properties / seats / items / properties / runner
      Added value: +{
+  "description": "Default \"research\" (the cloud runner claims it). \"local\" names a registered local/subagent agent_id -- only that agent, claiming as itself (tascan_claim_run instance starting with \"<agent_id>:\"), can claim the seat; it is never webhook-fired.",
+  "enum": [
+    "research",
+    "local"
+  ],
+  "type": "string"
+}
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, but the description adds substantial non-obvious behavior: budget is consumed BEFORE create, refusals visible only to the DB still consume units, the specific failure codes (cap_below_plan, fanout_ceiling_unset, over_ceiling, idempotency_body_mismatch), the 24h replay window, and that every seat, synth and roll-up leaves a signed completion.

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?

It is a dense single paragraph, but it is front-loaded with the core action and scoping constraint and nearly every sentence carries operational payload (auth, budget, failure codes, dry_run, idempotency, tracking). A long run of parenthetical failure codes makes it slightly hard to scan, keeping it just short of 5.

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 13-parameter, nested-object, no-output-schema tool this covers the operational essentials: auth prerequisite, budget side effects, validation path, failure modes, idempotency and where to track the result. The one gap is that the successful-create return payload is only partially implied (fanout_id appears only in the idempotency replay branch), so an agent cannot fully anticipate the normal response without an 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?

Schema description coverage is already 100%, so the baseline is 3, but the description adds genuine semantics beyond the schema for dry_run (returns dry_run/plan_sha256/seats/problems without spending budget), idempotency_key behavior, and the budget-consumption path around cap. It does not restate the remaining nested seat/synth/seat_defaults fields, which the schema already handles well.

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?

States a specific verb and resource ('Create a fan-out: 1-30 seats ... plus one synthesizer under ONE cycle root') and pins the endpoint POST /coord/fanouts. It also distinguishes the artifact from its siblings by naming the tracking tool (tascan_get_fanout) and clarifying what the operation does NOT do relative to the wider coordinator tree.

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 conditions for using dry_run as a preflight and for supplying idempotency_key, and states the required auth scope (agent:dispatch:code, with the note that an admin session has none). It does not explicitly contrast against sibling creation tools such as tascan_create_cycle or explain when a fan-out is preferred over delegating individual tasks, so it stops short of full when-not guidance.

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

All TaScan toolsInspect
Try in Browser
Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources