Skip to main content
Glama

Decide approval

dsh_approval_decide
Destructive

Allow or deny a pending DSH permission request during a running turn, letting the agent continue past sandbox or escalation checks.

Instructions

While a turn is running, decide a permission request DSH is waiting on (these only appear when the conversation uses on_approval=ask); after you allow or deny, the turn continues. It hands DSH's out-of-sandbox and escalation requests to the caller instead of allowing or denying them all. To grade the result of a finished turn use dsh_review.

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": {
      "conversation_id": "<conversation_id>",
      "approval_id": "<approval_id>",
      "decision": "<decision>"
    },
    "name": "dsh_approval_decide"
  }
}

Input Schema

NameRequiredDescriptionDefault
decisionYesAllow or deny.
approval_idYesFrom dsh_inbox, or pending_approvals in dsh_get.
conversation_idYesConversation id, from dsh_start or dsh_list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.6.8
    • changedInput schema / properties / approval_id / description
      Previous value: -"来自 dsh_inbox 或 dsh_get 的 pending_approvals。"New value: +"From dsh_inbox, or pending_approvals in dsh_get."
    • changedInput schema / properties / conversation_id / description
      Previous value: -"会话 id,来自 dsh_start 或 dsh_list。"New value: +"Conversation id, from dsh_start or dsh_list."
    • changedInput schema / properties / decision / description
      Previous value: -"放行或拒绝。"New value: +"Allow or deny."
  2. Changed1 schema field changedv0.6.5
    • changedInput schema / properties / approval_id / description
      Previous value: -"来自 dsh_get 的 pending_approvals。"New value: +"来自 dsh_inbox 或 dsh_get 的 pending_approvals。"
  3. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

Beyond the annotations, it usefully discloses the timing (requests only surface under on_approval=ask) and the consequence ("after you allow or deny, the turn continues"). However, destructiveHint=true and idempotentHint=false are never explained — the description doesn't say what a deny destroys or why re-invoking is unsafe, which is the most important missing behavior for a destructive decision tool.

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?

Three sentences, front-loaded with the timing precondition and closed with a sibling hand-off. The middle sentence is the only soft spot, but no sentence is filler and nothing essential is buried.

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, non-idempotent decision tool with no output schema, the definition covers when to call and what happens afterward but omits the consequences of each decision and what the call returns. Adequate to invoke correctly, not complete enough to invoke safely.

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?

All three parameters are already documented at 100% coverage, including the enum values and where approval_id and conversation_id come from. The description adds no syntax, format, or edge-case meaning beyond the schema, so the baseline of 3 applies.

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 gives a specific verb+resource ("decide a permission request") and scopes it to a running turn, which is enough for an agent to distinguish it from dsh_review. The middle sentence about handing "out-of-sandbox and escalation requests to the caller" is ambiguous — it describes the approval flow generally rather than this call's effect, slightly blurring the purpose.

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?

It states the operative condition clearly: use it while a turn is running, and such requests exist only when the conversation uses on_approval=ask. It also routes the agent away for a different goal ("To grade the result of a finished turn use dsh_review"). It does not cover what to do when nothing is pending (e.g., dsh_inbox fallback).

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