read_conversationFetches a conversation's messages with one user, oldest first, so you can review history and optionally mark them read.
Messages with one user, oldest first. Leaves them unread unless mark_read=true.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Items per page (max 200) | |
| before | No | Message id - returns the page of older messages | |
| user_id | Yes | ||
| mark_read | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false, and the description explains exactly why: reading has the state side effect of marking messages read only when mark_read=true. That is precisely the kind of non-obvious behavior annotations cannot convey, though return format and pagination mechanics are not covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero filler. Ordering comes first, the side-effect caveat second — both front-loaded where they matter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 4-param read tool with no output schema and partial annotation coverage, the description supplies the two things an agent cannot get elsewhere: sort order and the unread/mark_read side effect. Pagination via `before` is left to the schema, which is an acceptable but minor miss.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (limit and before are documented; user_id and mark_read are not). The description compensates for mark_read by stating its default behavior and side effect, which is the highest-value gap, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb+resource: reading messages with a single user, plus the ordering guarantee (oldest first). It clearly reads a single conversation, but it never names siblings like list_conversations or poll_messages to sharpen the distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Messages with one user" implies the per-conversation read versus the inbox listing, but the agent must infer that from the name plus sibling list. There is no explicit when-to-use, when-not, or named alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.