Skip to main content
Glama
agentisend

agentisend

Ask a human before sending

request_approval

Ask a person to approve sending large, unusual, or irreversible emails; nothing is sent and no budget is spent until the pending action is reviewed.

Instructions

Purpose: ask a person before sending. Reach for it when a send is large, unusual, irreversible, or something you were told to check first. NOT for: sending. NOTHING IS SENT and no budget is spent. No tool approves one, including this one. Returns: the action id, state pending, sent: false, and where a person decides it. list_agent_actions is how you hear the answer. A payload that would be refused anyway is refused here rather than queued, so nobody is asked to approve a send that cannot succeed.

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": {
      "from": "<from>",
      "to": "<to>",
      "subject": "<subject>",
      "reason": "<reason>"
    },
    "name": "request_approval"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesOne recipient address, or a list of up to 50. A bare string is fine.
fromYesSender address, e.g. "Acme <hello@acme.com>".
htmlNoHTML body. Provide html or text.
textNoPlain-text body. Provide html or text.
reasonYesWhy a person should look at this. Shown on the approval card.
subjectYesSubject line.
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
sentNoAlways false: asking sends nothing.
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
stateNo
action_idNoIdentifier.
check_withNoHow to hear the decision.
created_atNoISO 8601 time.
decided_by_human_atNoWhere a person decides it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only cover safety flags; the description adds what actually matters for an approval tool — nothing is sent, no budget is spent, no tool can self-approve, the returned state is pending with sent: false, and validation happens before queueing so a doomed send never reaches a reviewer. It also notes that failures surface here rather than in the approval queue, which is behavior an agent could not infer from the schema.

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 sections (Purpose / NOT for / Returns / validation note) front-load the decision-relevant facts, and each sentence carries a distinct piece of information. No restatement of the title or filler.

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?

With an output schema present, the description need not enumerate return fields, yet it still highlights the decisive ones (action id, pending, sent: false) and explains how the answer is retrieved. For a 7-parameter mutation-adjacent tool, nothing an agent needs in order to call it correctly is missing.

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 100%, so every parameter including idempotency_key already carries its own explanation. The description adds only indirect context — that the payload is validated at this step, so a 'reason' is shown to a human decider — without adding syntax or format detail beyond the schema. Baseline 3 applies.

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?

The first line names a specific verb and resource ('ask a person before sending') and immediately separates it from the act of sending with 'NOT for: sending.' An agent can distinguish this from send/list tools 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit trigger conditions (large, unusual, irreversible, or previously flagged sends), an explicit exclusion ('NOT for: sending'), and routes the agent to the right sibling for the outcome: 'list_agent_actions is how you hear the answer.' That is when-to-use, when-not, and the alternative in three sentences.

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