Skip to main content
Glama
DeepSeek Harness MCP Server

DeepSeek Harness MCP Server

dsh_respond_permission

Destructive

Answer one pending Harness tool permission by selecting allow_once or reject_once after inspecting pending permissions and tool calls; durable grants and workspace widening are unsupported.

Instructions

Answer one pending in-scope Harness tool permission once. Inspect pending_permissions and tool_calls first. Select allow_once only when the exact operation is user-authorized. This cannot widen the task workspace: danger-full-access or unknown-context requests are automatically rejected before becoming pending. Never bypass host approval rejections. Durable grants are unsupported.

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>",
      "permission_id": "<permission_id>",
      "decision": "<decision>"
    },
    "name": "dsh_respond_permission"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYes
decisionYes
permission_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true; the description goes beyond them by disclosing that danger-full-access or unknown-context requests are auto-rejected before becoming pending, that the tool cannot widen the task workspace, and that durable grants are unsupported. It does not say what happens to the pending request or the task after a reject_once, which is the main remaining behavioral gap.

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, each carrying a distinct constraint (preconditions, authorization gate, scope limit, host-approval warning, no durable grants). Front-loaded with the core action, with no filler or repetition.

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?

For a destructive, open-world mutation with no output schema and 0% schema coverage, the description covers constraints well but omits outcome information: what a successful answer returns, what an error looks like if the permission is no longer pending, and whether the decision is final. An agent could still call it, but cannot predict the response.

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 0%, so the description carries the burden for all three parameters. It clarifies the decision enum by naming 'allow_once' and tying permission selection to inspecting pending_permissions, but task_id is never mentioned and permission_id sourcing is only implied.

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: 'Answer one pending in-scope Harness tool permission once,' which tells an agent this resolves an approval request rather than creating or listing tasks. It is distinguishable from the sibling task-management tools, though it references 'pending_permissions' and 'tool_calls' as if they were known tools without identifying them among the siblings.

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 explicit preconditions ('Inspect pending_permissions and tool_calls first') and a gating rule for the affirmative path ('Select allow_once only when the exact operation is user-authorized'). It also warns against bypassing host approval rejections, but never states when reject_once is the right choice versus simply declining to act.

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