Skip to main content
Glama
agentisend

agentisend

Release a held received email

release_received_email
Idempotent

Releases a held received message so the domain delivers it and the approval row is marked decided. Pass a reason to record the decision on the audit row.

Instructions

Purpose: release one received message that a domain is holding. The arrival webhook fires once, and the approval row is marked decided. NOT for: mail that was not held. A clear message is already delivered. Pass a reason; it is kept on the audit row. Returns: the message, including held=false and inbound_verdict.

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": {
      "received_id": "<received_id>",
      "reason": "<reason>"
    },
    "name": "release_received_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesWhy this message is being released.
received_idYesThe id of the held message.
idempotency_keyNoYour own key for this action. Retrying with the same key returns the first result instead of doing it twice — send one whenever a retry could double the effect.

Output Schema

NameRequiredDescriptionDefault
idNoIdentifier.
heldNoFalse after a release.
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
verdictNoclear, review, or unavailable.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds real side-effect detail beyond that: the arrival webhook fires once, the approval row is marked decided, and the reason persists on an audit row. It omits whether retries without an idempotency key could double-fire the webhook, which is the one 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Labeled Purpose / NOT for / Returns blocks make it scannable, and the primary purpose plus the exclusion are front-loaded. Every sentence carries information; nothing restates the tool name or the annotations.

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 mutating, non-destructive, idempotent action with an output schema, this covers purpose, exclusion, side effects, and the audit trail. Missing only a note on permissions or what state the message must be in (e.g. pending approval) before release succeeds.

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 100%, so the baseline would be 3. The description still adds meaning the schema does not: the reason is retained on the audit row, which tells an agent the field has downstream visibility rather than being throwaway metadata. It says nothing extra about received_id or idempotency_key, but those are well documented in the schema.

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 and resource with scope: 'release one received message that a domain is holding'. It also draws a boundary against non-held mail, which lets an agent separate this from get_received_email or list_received_emails without opening a schema.

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?

The 'NOT for: mail that was not held. A clear message is already delivered' line gives an explicit exclusion criterion, which is the main failure mode for this action. It does not name a concrete alternative tool (e.g. list_pending_approvals to find held mail), so the routing is slightly less complete than it could be.

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