Skip to main content
Glama

Decide whether to send to an email

decide_send

Decide whether to send an email to one address. Returns one action (send, send_with_caution, review, retry_later or avoid) with a reason and a machine-readable reason_code, a 0-100 confidence, the verification status, the mail provider, a did_you_mean typo suggestion, risk signals (catch_all, disposable, free, role_account) and the credit cost. Costs 1 credit; checking the same address again within 72 hours is served from cache for free, and malformed addresses and results we can't resolve (greylisting, or an unknown with no catch-all or disposable signal) are free. Use this before sending to a single address; use verify_email when you need full mailbox detail, and create_verify_batch for lists.

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": {
      "email": "<email>"
    },
    "name": "decide_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailYesThe email address to check, for example jane@example.com.
strictnessNoHow cautious the recommended action is. default: catch-all domains get review. aggressive: catch-all domains get send_with_caution. strict: as default, and role addresses such as info@ or sales@ also get review. Defaults to default.
force_refreshNoSkip the 72-hour cache and verify again now. Costs 1 credit even when a cached result exists. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), it discloses the credit economics in detail: 1 credit per call, free on 72-hour cache hits, free for malformed addresses and unresolvable results such as greylisting or an unknown with no catch-all/disposable signal. It also enumerates the return payload (action, reason_code, confidence 0-100, verification status, provider, typo suggestion, risk signals), which the annotations alone would never convey. Nothing contradicts the annotations – a credit-consuming call is consistent with readOnlyHint=false.

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?

The purpose is front-loaded and the alternative-routing sentence sits at the end where it is actionable. The middle sentence packing seven return fields and a five-item action list is dense but earns its space given there is no output schema; it could be trimmed slightly without losing meaning.

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 no output schema, the description carries the burden of describing return values, and it does so field by field. Combined with the cost/cache rules and the strictness behavior, an agent has everything needed to call this correctly and interpret the result.

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 enum meanings for strictness are already carried by the schema. The description still adds value by tying the 72-hour cache window to the cost implications of force_refresh, which deepens understanding of that parameter beyond its schema text.

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 description pairs a specific verb and resource ("Decide whether to send an email to one address") with an explicit enumeration of the possible outcomes (send, send_with_caution, review, retry_later, avoid) and the shape of the return. It names the sibling alternatives, so an agent can distinguish this single-address decision tool from verify_email and create_verify_batch immediately.

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 an explicit timing rule ("Use this before sending to a single address") and routes to alternatives with their selecting conditions: verify_email for full mailbox detail, create_verify_batch for lists. Both the when-to-use and the when-to-use-something-else are stated rather than inferred.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources