Skip to main content
Glama
agentisend

agentisend

Explain what happened to an email

explain_email
Read-onlyIdempotent

Diagnose a single email's outcome after a bounce, complaint, or failure by returning the verdict, supporting evidence, retry feasibility, and callable remediation steps.

Instructions

Purpose: understand one message's outcome and act on it. Use it after a bounce, a complaint or a failure instead of guessing. NOT for: the raw timeline (get_email), or the state of the whole key (why_was_this_not_sent). Returns: the verdict, the evidence behind it (diagnostic code, feedback type, transport reason), whether retrying the identical send can work, and remediation as callable steps — each carrying the method, path and body. A step with no call is one only a person can do.

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_id": "<email_id>"
    },
    "name": "explain_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
email_idYesThe message id returned by send_email.

Output Schema

NameRequiredDescriptionDefault
idNoIdentifier.
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
statusNo
actionsNo
verdictNo
evidenceNo
retryableNo
what_happenedNo

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 carry the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real substance beyond them: the verdict, its evidence sources, whether an identical retry can succeed, and that remediation arrives as callable steps while steps without a call require a human. It stops short of discussing auth or rate-limit behavior, but for a read-only diagnostic that is minor.

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?

Front-loaded with Purpose, then NOT for, then Returns, which is an effective order. It is slightly longer than necessary, including a mild rhetorical phrase ('instead of guessing') and a returns section the output schema already covers, but no sentence is genuinely wasteful.

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?

Given one required parameter, 100% schema coverage, rich annotations, and an existing output schema, the description supplies everything missing: purpose, routing, and the nature of the returned diagnosis and remediation. No behavioral or selection gap remains.

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% and the single parameter is fully documented as the message id returned by send_email. The description adds no syntax, format, or edge-case guidance for email_id beyond what the schema already supplies, so the 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?

States a specific verb and resource (explain one message's outcome and remediation) and explicitly names the sibling tools it is not (get_email, why_was_this_not_sent). An agent can distinguish it from near-neighbors without opening any 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?

Gives explicit when-to-use ('after a bounce, a complaint or a failure instead of guessing') and explicit when-not-to-use with named alternatives for the raw timeline and whole-key state. Nothing about routing is left to inference.

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