Skip to main content
Glama

SalesBlink Cold Email

Update Mail State

update_mail_state
Destructive

Update Mail State - Mark emails as read/unread or update outcome

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": {
      "messageId": "<messageId>"
    },
    "name": "update_mail_state"
  }
}

Input Schema

NameRequiredDescriptionDefault
unreadNoMark as read (false) or unread (true)
outcomeNoSet the conversation outcome
messageIdYesThe message ID
workspace_idNoWorkspace ID this action applies to. When omitted, the current or default workspace is used.

Output Schema

NameRequiredDescriptionDefault
resultNoThe raw result returned by the SalesBlink tool.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / outcome / description
      Previous value: -"Set the outcome (e.g., 'positive')"New value: +"Set the conversation outcome"
    • addedInput schema / properties / outcome / enum
      Added value: +[
      +  "interested",
      +  "not-interested",
      +  "meeting-request",
      +  "out-of-office",
      +  "automatic-response",
      +  "do-not-contact",
      +  "wrong-person",
      +  "closed"
      +]
  2. First observed

TDQS

C2.9/5.0
Behavior2/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's job is to explain what is actually destroyed or overwritten — it does not. An agent cannot tell whether setting outcome replaces a previously recorded outcome, whether changes are reversible, or whether workspace-level permissions are required. The destructiveHint=true label is especially confusing for a read/unread toggle, and nothing here resolves that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

A single short sentence, so nothing is bloated, but the leading 'Update Mail State -' merely echoes the title and consumes the front-loaded position that should carry the actual capability statement. The remaining clause is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return values are covered by the output schema and all four parameters are fully specified, so the structured data carries most of the load. However, for a mutating tool flagged destructive with no annotations explaining scope of effect, the description leaves a real gap about what happens to existing state and which workspace context applies.

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 every parameter, including the outcome enum and the workspace_id fallback behavior, is documented in the schema itself. The description adds no syntax, default, or interaction detail beyond repeating the two fields already described. Baseline 3 is appropriate.

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?

The description names a specific verb (update) and the two state dimensions it can change (read/unread flag and conversation outcome), which is more than a title restatement. No sibling tool touches per-message state, so confusion risk is low, though it never says what a 'mail state' object is or which message is targeted (the required messageId is only visible in the schema).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no guidance on when to use this versus adjacent tools such as update_lead, move_lead, or unsubscribe_lead_from_sequence, even though 'outcome' values like do-not-contact and wrong-person clearly overlap with lead-level operations. No prerequisites, no note on whether both unread and outcome can be set in one call.

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.