Skip to main content
Glama

Email: Mark read

email_mark_read
Destructive

Mark one exact email read. Resolve human email reference -> email_id first. Email provider ID: Exact email ID returned by Nilyo for the connected mailbox. On IMAP (and Exchange over IMAP) the ID encodes folder + UID: it CHANGES when the email is moved or a draft is updated; always reuse the id returned by the last operation. Obtain with: email_list_messages or email_list_folder_messages -> email.id; the id returned by email_move_or_label / email_update_draft after a change Never pass: RFC Message-ID unless a tool explicitly documents it, subject, an email_id captured before a move/update on IMAP.

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": "email_mark_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
email_idYesExact provider email ID from email list/read/resolve. Email provider ID: Exact email ID returned by Nilyo for the connected mailbox. On IMAP (and Exchange over IMAP) the ID encodes folder + UID: it CHANGES when the email is moved or a draft is updated; always reuse the id returned by the last operation. Obtain with: email_list_messages or email_list_folder_messages -> email.id; the id returned by email_move_or_label / email_update_draft after a change Never pass: RFC Message-ID unless a tool explicitly documents it, subject, an email_id captured before a move/update on IMAP.
account_idNoOptional Nilyo connection ID (unipile_account_id from list_connected_accounts). Omit when the user has one account for this provider. When several exist, Nilyo never guesses: list them (display name, identifier, provider user ID), choose the one the user named or ask, and pass its ID here.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / email_id / description
      Previous value: -"Exact provider email ID from email list/read/resolve. Email provider ID: Exact email ID returned by Nilyo/Unipile for the connected mailbox. On IMAP (and Exchange over IMAP) the ID encodes folder + UID: it CHANGES when the email is moved or a draft is updated; always reuse the id returned by the last operation. Obtain with: email_list_messages or email_list_folder_messages -> email.id; the id returned by email_move_or_label / email_update_draft after a change Never pass: RFC Message-ID unless a tool explicitly documents it, subject, an email_id captured before a move/update on IMAP."New value: +"Exact provider email ID from email list/read/resolve. Email provider ID: Exact email ID returned by Nilyo for the connected mailbox. On IMAP (and Exchange over IMAP) the ID encodes folder + UID: it CHANGES when the email is moved or a draft is updated; always reuse the id returned by the last operation. Obtain with: email_list_messages or email_list_folder_messages -> email.id; the id returned by email_move_or_label / email_update_draft after a change Never pass: RFC Message-ID unless a tool explicitly documents it, subject, an email_id captured before a move/update on IMAP."
  2. First observed

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false, so the mutation profile is structured data. The description adds genuinely useful behavior — that IMAP IDs change after a move or draft update — but says nothing about reversibility (email_mark_unread exists) or why the operation is flagged destructive, which is the exact gap an agent would want covered.

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?

The purpose sentence is front-loaded and short, but the remaining bulk is a dense, run-on ID paragraph that restates schema text and mixes obtain/never-pass rules without formatting. Repetition of the schema's field description is wasted space relative to this tool's scope.

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?

For a simple two-parameter mutation with full schema coverage and annotations, the definition is adequate on inputs. It omits the one thing the annotations cannot convey — that the change is reversible via email_mark_unread and syncs to the provider mailbox — leaving the destructiveHint flag unexplained.

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 description's ID paragraph duplicates the email_id field description nearly verbatim, so it adds no meaning beyond the schema. The second parameter, account_id, is not addressed at all in the description.

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?

"Mark one exact email read" gives a specific verb and resource, and the word 'read' implicitly separates it from the email_mark_unread sibling. It does not explicitly name that sibling or state the distinction, so it falls short of full sibling differentiation.

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

Usage Guidelines3/5

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

The description provides a precondition workflow ('Resolve human email reference -> email_id first') and lists where to obtain the ID, which is useful procedural guidance. It never states when to use this versus email_mark_unread, nor any exclusion or undo path, leaving usage largely implied.

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.