Skip to main content
Glama

Read a conversation

get_conversation

Reads one thread whole: every message in order with its direction, its language and its attachments, the contact fiche, the mailbox the thread arrived through, the draft awaiting review when there is one, and in "notes" what the team left on the thread for each other, oldest first, with who wrote each one. Notes are never part of "messages" and were never sent to anyone. A message the mailbox sent carries "delivery" when the mail system tracked it: per recipient (Bcc included), "state" is "delivered" (accepted by the recipient's server, which says nothing of the inbox or of reading), "deferred" (retried by itself for five days), "bounced", "returned" (accepted, then a non-delivery report came back) or "expired", with the server's own "remote_reply" and a "reason" in plain words. When the thread was filed as it arrived, "filed_reason" says why: "spam_filter" for the filter's verdict, "blocked_sender" for a sender the account had reported, and "spoofed_own_domain" for a mail showing one of the account's own domains whose DMARC check failed, which lands in Spam in a mailbox (mark_not_spam takes it back out) and, on a helpdesk queue, in the Trash with its ticket closed (file_conversation with "inbox" brings it back, open). Read this before writing an answer. To read several threads, give conversation_id the list of their ids, in ONE call rather than one call per thread: the answer then lists in "results" the outcome of each thread in the order given ("ok", with its "result" or its "error") and counts "succeeded" and "failed". Each thread passes exactly the checks it would alone, so one refused or out of reach ("not found") leaves the others done, and the call is an error only when none succeeded.

Input Schema

NameRequiredDescriptionDefault
conversation_idYesThe id of the conversation, as list_conversations gives it, or a list of up to 20 ids to do the same to every one of them in a single call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: it explains the exact shape of the response, clarifies that notes are never part of messages and were never sent, documents delivery states and filed_reason semantics, and describes per-thread error handling in batch mode. This is unusually thorough behavioral disclosure.

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 description is a single dense paragraph with many detailed clauses. While information-rich, it could be structured with bullets or shorter sentences for readability; some details (e.g., the full delivery-state taxonomy) are arguably more than an agent needs upfront to decide to call the tool.

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

Completeness4/5

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

There is no output schema or annotations, so the description must carry return-value explanation, which it does extensively. It is nearly complete, though it does not mention pagination or size limits on the message list, which could matter for very large threads.

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 baseline is 3. The description adds value by explaining the batch outcome structure ('results', 'succeeded', 'failed') and the all-or-nothing error condition, which goes beyond the schema's simple note that a list is accepted.

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 opens with a precise verb and resource: 'Reads one thread whole: every message in order...' and enumerates exactly what is returned. An agent can distinguish this from list/search tools because it is clearly a full-thread fetch with batch support.

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?

It explicitly says 'Read this before writing an answer' and explains that to read several threads you should pass a list of ids in ONE call rather than one call per thread. It does not name which sibling to use for finding conversation ids or when not to use this tool, but the usage context is clear.

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