delega-mcp

register_human_request

Registers an immutable checklist on an existing open, evidence-required human-request task, validating expected revision so equal retries replay and different input conflicts.

Instructions

Register one immutable checklist on an existing open, unclaimed, autopilot-hold, evidence-required task assigned to the configured human-request runtime. Recipient is the existing self chat. Equal retries replay; different input conflicts. Registration does not send, run, claim, or grant execution approval. Hosted API must enable this feature.

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": {
      "task_id": "<task_id>",
      "criteria": "<criteria>",
      "expected_revision": "<expected_revision>"
    },
    "name": "register_human_request"
  }
}

Input Schema

Name	Required	Description
`task_id`	Yes	Existing task's exact internal ID
`criteria`	Yes
`timeout_seconds`	No	Bounded run length; default 1200 seconds
`expected_revision`	Yes	Current task revision

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.19.1Oct 27, 2026

TDQS

A4.6/5.0

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 does so well: it discloses immutability, idempotency semantics (equal retries replay, different input conflicts), the recipient (self chat), the absence of side effects (does not send, run, claim, or grant approval), and a feature-flag prerequisite.

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 dense sentences, front-loaded with the core action and preconditions, followed by idempotency, non-effects, and the feature gate. No filler; every sentence adds operational information.

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 mutation-style registration tool with no output schema and no annotations, the description covers preconditions, idempotency, side effects, and environment gating thoroughly. The main remaining gap is what registration returns or how to retrieve the registered request, which the agent must infer from sibling tools like get_human_request.

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 75%, so most parameters are already documented. The description adds meaning beyond the schema by explaining that criteria form an immutable checklist and by clarifying replay/conflict semantics that govern expected_revision and input equality. It does not add per-parameter details for timeout_seconds or criteria constraints, which the schema already covers.

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 (register) and resource (one immutable checklist / human request) and pins down exactly which task it applies to: an existing open, unclaimed, autopilot-hold, evidence-required task assigned to the human-request runtime. It also distinguishes itself from send/run/claim/approval actions, which separates it from siblings like claim_task, complete_task, cancel_human_request.

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 rich preconditions (task state, runtime assignment, feature flag on hosted API) that tell an agent when the call will succeed. It does not explicitly name alternatives such as get_human_request/get_human_result for polling results, so the when-to-use-vs-alternative routing is only implied.

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