Skip to main content
Glama

casting_call

Auditions 2–24 personas against a brief, cross-examines their claims, flags redundancy and gaps, and recommends a cast roster. Optionally runs static dry-run checks without provider calls.

Instructions

Audition 2 to 24 personas for any brief. A neutral casting director cross-examines their claims, identifies redundancy and gaps, and recommends a cast (with duel teams when at least four seats are requested). Returns the roster in markdown, archive id and usage. Runs the whole casting call with progress notifications on every visible step. dry_run performs static checks without keys or provider calls.

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": {
      "brief": "<brief>"
    },
    "name": "casting_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
mixNoPrefer lower-cost providers using the table's routing judgment.
seatNoOptional assignments keyed by exact persona identifier: {"designer":{"provider":"anthropic","model":"sonnet"}}. Each entry accepts agent, provider (a provider or explicit runtime name) and model.
briefYesThe brief the personas audition for.
modelNo
seatsNoRecommended cast size; default min(5, personas). Must be a whole number.
agentsNoPersona identifiers; omitted means every persona in agents_dir.
dry_runNoOnly local lint and overlap checks; no provider calls or keys.
examineNoCross-examine personas after their auditions; default true.
providerNoOmit or use auto for provider judgment (the router picks a healthy provider per seat and reports why in a routing block); otherwise the chosen provider is used as given. Options: auto; anthropic; openai; together (Together AI — any Together model id, e.g. zai-org/GLM-5.3 or Qwen/...); replicate (owner/name, owner/name:version, or https://replicate.com/owner/name); ollama (local, only when reachable); openai_compatible (any /v1/chat/completions server — set OPENAI_COMPATIBLE_BASE_URL or pass base_url).
agents_dirNoAbsolute persona directory.
connectorsNoOptional names of configured MCP connectors (roundtable config set connector) that every seat may call as tools during its turn. Only read-only tools are offered unless the connector's config lists more; tool results are untrusted data and are scrubbed. Seats on providers without tool support (Replicate) speak without them. An unknown connector is an error before any provider call.
max_secondsNoWhole-run deadline; default 300 seconds. Stops new calls and archives available results.
turn_timeout_sNoSeconds per turn; default 90.
seat_connectorsNoOptional per-seat limits, used with connectors: a map from a seat (agent) name to the subset of connectors that seat may call, e.g. {"ada": ["figma"], "bob": ["jira"]}. A seat not listed gets all of the session's connectors; an empty list gives that seat none. Every connector named must also be in connectors, and every seat must be at the table; otherwise the call fails before anything starts.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), the description discloses that the run makes provider calls, emits progress notifications on every visible step, and produces an archive id plus usage data. It also explains the dry_run escape hatch that avoids keys and provider calls, which is genuinely useful behavioural context for a non-idempotent, open-world operation.

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?

Five short sentences, front-loaded with the core action and followed by output, execution behaviour, and the dry-run option. No filler, though the dry_run sentence largely duplicates the schema's own parameter description.

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 14-parameter, nested-schema tool with no output schema, the description usefully covers the return shape (markdown roster, archive id, usage) and runtime behaviour (progress notifications, dry_run). Complex parameters like connectors, seat_connectors, and max_seconds are left entirely to the schema, but that coverage is strong enough not to leave a critical gap.

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 93%, so the schema already carries parameter meaning. The description mostly restates what the schema documents (dry_run's no-key/no-provider behaviour, seat count driving duel teams) and adds no syntax or format detail beyond it; baseline 3 is appropriate.

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?

The description opens with a concrete verb and resource: 'Audition 2 to 24 personas for any brief', then explains the casting-director cross-examination and the markdown roster/archive output. It is clearly distinct from the collaboration/execution siblings, though it never names an alternative tool to reinforce that distinction.

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?

It gives situational context (any brief, 2-24 personas, duel teams when at least four seats are requested) and clarifies that dry_run does static checks without keys or provider calls. However, it never states when an agent should choose this over a chat/collaboration tool, nor any explicit exclusions or prerequisites.

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