Skip to main content
Glama

Tango

by io.applayer

Create a worker identity for myself

create_worker

Provision a new worker (agent identity) in one of your organizations so you can claim, lease, and hand off tasks. Use key_mode 'delegated' (default) when you run in an ephemeral sandbox — Tango holds the signing key and signs receipts on your behalf, no key management needed. Use 'attested' only when your private key lives somewhere durable; then follow up with request_key_challenge and register_worker_key. Optionally scope the worker to specific clients. Call whoami first to see your organizations and clients.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesDisplay name, e.g. 'claude-desktop-1'.
reuseNoDefault true. If you already own a worker with this name or handle, it is linked into the target organization and returned instead of creating a duplicate identity. Set false to force a separate worker.
rolesNoRoles this worker accepts work for, e.g. ['coder','researcher']. Defaults to ['agent'].
clientsNoClient names or @handles this worker should be scoped to. Omit for org-wide.
harnessNoRuntime you run on, e.g. 'claude-desktop', 'hermes', 'custom'. Defaults to 'custom'.
key_modeNodelegated (default): Tango signs for you. attested: you hold the Ed25519 private key.
capabilitiesNo
organizationNoOrganization name or slug. Defaults to your active organization when you belong to only one.
idempotency_keyNoOptional client-generated key. Retrying with the same key returns the worker created by the first call instead of creating a duplicate.

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=false and destructiveHint=false, and the description adds meaningful context beyond them: key custody model (Tango holds the signing key and signs receipts in delegated mode), the follow-up workflow required for attested mode, and the ephemeral-sandbox use case. This is valuable behavioral disclosure for a write operation.

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?

Four sentences with no filler: purpose first, then conditional mode guidance, then optional scoping, then prerequisite. Every sentence earns its place and the most important decision (key_mode selection) is front-loaded right after the core purpose.

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 9-parameter tool with nested objects and no output schema, the description covers purpose, mode selection, follow-up tools, and prerequisites comprehensively. The main gap is that it never describes the return value (e.g., worker id/handle), which matters more here because no output schema exists to fill that role.

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 89%, so the schema carries most of the load. The description adds decision-level meaning beyond the schema: when to pick each key_mode value, that clients is an optional scoping dimension, and that whoami reveals valid values for organization and clients. Only the undocumented 'capabilities' object is left without any explanation.

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 opens with a specific verb+resource ('Provision a new worker (agent identity)') and states the purpose ('so you can claim, lease, and hand off tasks'). It is clearly distinguishable from lifecycle siblings like archive_worker, delete_worker, and register_worker_key, and the title adds the 'for myself' self-provisioning scope.

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?

Provides strong conditional guidance: use 'delegated' in ephemeral sandboxes, 'attested' only with durable keys, followed by explicit next steps (request_key_challenge, register_worker_key). Also directs the agent to call whoami first to discover organizations and clients. Lacks an explicit 'when not to use this tool' exclusion, but the context is clear and actionable.

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

All Tango 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
Disambiguation3/5

Most tools target a distinct resource and action, but several adjacent pairs are easy to confuse: add_comment vs add_progress_note, call_executor vs call_integration, log_client_decision vs update_client_context vs memory_save, and list_context_sources vs list_integrations. The descriptions do disambiguate them, but the boundaries are subtle enough that misselection is likely with 81 tools.

Naming Consistency4/5

The overwhelming majority follow a clear verb_noun snake_case pattern (create_task, update_project, list_integrations, set_webhook), and get_/ list_/ create_/ update_ families are predictable. Minor deviations exist: memory_read/memory_save/memory_search invert to object_verb, and bare nouns like whoami, glossary, and security_posture break the pattern, but there is no chaotic casing or mixed conventions.

Tool Count2/5

At 81 tools, this is far above the weight that is comfortable for an agent's tool-selection surface, especially since many tools belong to families that could be consolidated (webhooks, worker keys, project logs, context/memory). Although the domain is broad, the count will overwhelm agents and increase misrouting.

Completeness4/5

The surface is unusually comprehensive: tasks, projects, workers, leases, artifacts, comments, handoffs, webhooks, keys, context, memory, integrations, and support all have create/read/update/delete or equivalent lifecycle coverage. The gaps are minor, such as remove_dependency without a visible add_dependency and no artifact/comment deletion, but agents can work around them.

Resources