okto-nexus

Overview Schema Source Related Servers Discussions Admin

handoff_create

Create an open handoff with validated target and visibility, then poll its status and result via handoff_get.

Instructions

Create an OPEN handoff (validates target/visibility); emit handoff.created. After creating, poll handoff_get for status/result. Full docs: okto-nexus://reference/tool-docs/handoff.

Input Schema

TableJSON Schema

Name	Required	Description
`target`	Yes	Routing target as a raw JSON object - which agents may CLAIM this handoff (REQUIRED). strategy one of: direct {"strategy":"direct","agent_id":"<id>"}; capability {"strategy":"capability","capability":"<cap>"}; role {"strategy":"role","role":"<role>"}; tag {"strategy":"tag","selector":{"<key>":["<value>",...]}} (flat: AND across keys, OR within values) or rich [{"key":"<k>","operator":"In\|NotIn\|Exists\|DoesNotExist","values":["<v>",...]}] (ANDed; CAUTION: NotIn/DoesNotExist also match agents MISSING the key); broadcast {"strategy":"broadcast"}; mixed {"strategy":"mixed","rules":[<sub-target>,...]}; direct_with_fallback {"strategy":"direct_with_fallback","agent_id":"<id>","fallback_after_seconds":<n>}. Competing-consumers: the first to handoff_claim wins. Hierarchy/catalog rules, examples, edge-cases: okto-nexus://reference/target-grammar.
`payload`	No	Inline work content (optional; raw JSON object/array, string, or null - NOT JSON-encoded). Returned only to the claimant by handoff_claim / claimant handoff_get. For large content pass an artifact_id.
`trace_id`	No	Trajectory trace_id to stamp on this handoff (optional; non-empty string, max 128 chars). Needs the feature_trace flag ON, else accepted and ignored; omitted = generate one.
`verify_by`	No	Who verifies (optional; only WITH acceptance_criteria; raw JSON object). one of: {"kind":"creator"} (default); {"kind":"agent","agent_id":"<id>"} (must be registered); {"kind":"capability","capability":"<name>"} (in the catalog; resolved at verify time). The claimant never verifies their own delivery.
`depends_on`	No	Handoff ids this one depends on (optional; raw JSON list of 1..20 unique existing ids; IMMUTABLE). Blocked - unlisted/unclaimable - until ALL are COMPLETED. Needs feature_dag ON (rejected while OFF).
`session_id`	No	Session_id attributing this operation to a specific open session of yours (optional).
`visibility`	Yes	Who may SEE the handoff (separate from who may CLAIM it = target). one of: public, eligible, private. REQUIRED (case-insensitive).
`project_root`	Yes	Absolute path to the project (defines the workspace scope).
`from_agent_id`	Yes	Your agent_id (the creator); recorded as the handoff's originator - the owner is whichever agent later claims it (handoff_claim), not necessarily you.
`acceptance_criteria`	No	Verification contract (optional; raw JSON list of 1..20 unique non-empty strings, max 500 chars each; IMMUTABLE). handoff_complete then parks the handoff in VERIFYING until the handoff_verify verdict. Needs feature_verification ON (rejected while OFF, never ignored).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.10Sep 28, 2026

TDQS

A3.5/5.0

Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It discloses that target/visibility are validated, that a 'handoff.created' event is emitted, and that status/result should be polled via handoff_get. However, it omits permissions, error handling, or side effects like ownership transfer, leaving significant gaps.

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 three tightly written sentences: front-loaded action, validation, event, next step, and a documentation link. Every sentence earns its place with no redundancy.

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

Completeness3/5

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

Given 10 parameters, no annotations, and an output schema that covers return values, the description is partially complete: it names the creation, validation, event emission, and follow-up poll. But it omits failure modes, required permissions, and other behavioral traits needed for a complex coordination tool, relying heavily on the external doc link.

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 100%, so the schema already documents all 10 parameters thoroughly. The description only reiterates that target/visibility are validated and adds no parameter syntax or meaning beyond the schema, making the baseline 3 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 states a specific verb ('Create') and resource ('handoff') with additional state ('OPEN') and validation scope ('validates target/visibility'). It clearly identifies the operation, though it does not explicitly differentiate from siblings like handoff_claim beyond the verb 'Create'.

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 implies when to use by stating the next step ('After creating, poll handoff_get for status/result'), but gives no explicit when-not conditions or alternative selection guidance relative to other handoff tools (claim, complete, etc.). Usage is only implied.

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