AIWorkhub

by shrec

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

aiworkhub_agent_retry_finalization

COORDINATOR/WRITE-GATED: retry one retained finalization request.

Instructions

COORDINATOR/WRITE-GATED: retry one retained finalization request.

The provider/model is never launched again. The exact successful worker request, retained workspace, task identity and supervisor exit receipt are revalidated before deterministic validation/finalization is re-entered. A validation failure is eligible only when its durable reason is the operational validation_exec_scratch_unavailable condition; ordinary product/test failures remain non-retryable. A scope_rejected request is eligible: the re-run repeats the scope check and reaches review_ready only if the retained delta is now in scope (NF-2026-01345).

validation_lane="manager_host" is the manager's explicit opt-in for a candidate whose declared validations failed only because the sandbox validation lane cannot execute them (NF-2026-01030). It makes any validation_failed/finalize_failed request whose retained candidate seal still verifies retryable, and re-runs the SAME declared commands with the validation route forced to the host backend. All pass -> the normal finalize path to review_ready; any failure -> validation_failed again, now with host receipts. The lane is never derived from candidate output. manager_host applies only to VS Code LM adapters: its forced backend is the editor-hosted one, which never runs a native CLI route outside its OS sandbox, so a request from a CLI adapter (e.g. claude_cli) is refused up front with validation_lane_forbidden_for_adapter:<adapter> before any event write or card transition, leaving the request and card unchanged (NF-2026-01645).

Input Schema

Name	Required	Description	Default
`task_id`	Yes
`request_id`	Yes
`validation_lane`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 20, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and delivers rich detail: it states the provider/model is never relaunched, that prior artifacts are revalidated, that re-entry is deterministic, that the lane is never derived from candidate output, and that the refusal path writes no event or card transition. These are exactly the operational traits an agent cannot infer.

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?

The core operation is front-loaded in the first line, and every subsequent paragraph adds distinct eligibility or refusal detail. It is dense and jargon-heavy, but for a coordinator/write-gated tool with complex semantics, the length is largely earned.

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?

Given no annotations, an output schema exists, and the tool is complex and write-gated, the description covers the call contract, eligibility gates, failure modes, adapter restrictions, and state-preservation guarantees. An agent has everything needed to decide whether to call it and what to expect.

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 0%, so the description must compensate. It explains the non-obvious `validation_lane` parameter in depth (opt-in for manager host, forced backend, adapter restriction) and implicitly explains `request_id` via 'retained finalization request' and `task_id` via 'task identity revalidated'. The only small gap is no explicit format hint for the two IDs.

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?

States a specific verb and resource: 'retry one retained finalization request' with a 'COORDINATOR/WRITE-GATED' qualifier. An agent can tell it is a retry operation for finalization, but the description never names which sibling tools (e.g., aiworkhub_task_retry_terminal or aiworkhub_agent_accept_review) are alternatives, so sibling differentiation is missing.

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?

Explicitly defines when the tool is eligible: validation failures only for the `validation_exec_scratch_unavailable` condition, `scope_rejected` requests, and the `validation_lane='manager_host'` opt-in for VS Code LM adapters only. It also specifies when it is refused: CLI adapters get `validation_lane_forbidden_for_adapter:<adapter>` up front. This is unusually thorough when/when-not guidance.

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

Deploy Server