Skip to main content
Glama

What happened to a draft

crm_draft_outcome
Destructive

Record that a person sent a draft, or that they rejected it. Sending happens in their mailbox; this records it. SENT: the person sent it themselves and is telling you so. sent_at is when it actually went, which is not when this got typed (CRM-5). The draft's exact text is copied onto the activity trail as the record of what reached a real person, and the draft becomes immutable from that moment (CRM-15). An account still sitting at not_started or researching moves to approaching, because it has now been approached — that is a fact, not a forecast.

DISCARDED: a person read it and said no. rejected_because is for whoever writes the next one, so "too long, and it opened on us rather than on them" is worth typing and "no" is not.

Never record a send you were told about by nobody. If you did not hear it from your human, ask; a send that did not happen is the one fact in this system that can embarrass a person in front of a stranger. Effects: draft closed as sent or discarded; a sent draft is copied onto the activity trail; account moved to approaching on first send.

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": {
      "draft_id": "<draft_id>",
      "outcome": "<outcome>"
    },
    "name": "crm_draft_outcome"
  }
}

Input Schema

NameRequiredDescriptionDefault
outcomeYesWhat the person did with it.
sent_atNoWhen it actually went. Required when sent. ISO date, YYYY-MM-DD.
draft_idYesThe draft, e.g. D-0001.
rejected_becauseNoFor discarded: why, so whoever writes the next one has something to go on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: the draft becomes immutable at that moment, its exact text is copied onto the activity trail, an account at not_started/researching is moved to approaching, and there is a closing Effects line. Permission-free but consequence-rich details like irreversibility and status side effects are exactly what an agent needs before a write.

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 the core action, then split into SENT / DISCARDED branches and a closing Effects line, which makes it scannable despite its length. The Effects line largely restates what the branch paragraphs already said about copying to the activity trail and moving the account, so a sentence of redundancy could be cut.

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?

For a destructive four-parameter mutation with no output schema, the description covers the decision rule, both enum branches, the conditional requirement of sent_at, the irreversibility, and the downstream account-status change. Nothing an agent needs to call this correctly is missing.

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 already 100%, so the baseline is 3, but the prose adds genuine meaning: sent_at is when the message actually went rather than when the record was typed (CRM-5), and rejected_because is framed for the next author with an example of a useful value versus a useless 'no'. These are quality-of-input cues the schema alone does not convey.

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?

States a specific verb and resource: record that a person sent or rejected a draft, with the explicit clarification that the actual sending happens in their mailbox and this only records it. That scoping sentence separates it well from a generic draft-mutation tool, but it never names the nearest sibling (crm_update_draft) to say which one an agent should pick.

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?

Gives clear per-branch conditions: SENT when the person sent it themselves and is telling you so; DISCARDED when a person read it and said no. It also states an explicit negative rule — never record a send you were not told about by your human, ask first — which is real when-not-to-use guidance. It stops short of pointing to an alternative tool for the 'not yet sent' case.

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.