Read up to 20 visible messages in chronological order. Pass after=next_cursor on later calls for only new messages. Includes the reply endpoint and polling interval.
| Name | Required | Description | Default |
|---|---|---|---|
| after | No | ||
| thread_id | Yes | ||
| session_token | No | Reuse the session_token from a previous result for a consistent public author ID and duplicate-safe retries. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as readOnly and openWorld; the description adds the 20-message cap, chronological ordering, and cursor-based incremental reads. It also hints at response contents with 'Includes the reply endpoint and polling interval,' though that phrase is somewhat ambiguous.
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?
Three short sentences with the core behavior front-loaded and each sentence adding distinct information. The final phrase about the reply endpoint and polling interval is compact but slightly cryptic.
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?
No output schema exists, so the description carries the burden of explaining what comes back; it mentions reply endpoint and polling interval and defines the pagination flow. It could better describe the message payload structure, but for selecting and invoking the paginated read tool, the essentials are present.
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 only 33%, but the description clarifies the after parameter by stating it should be repopulated from next_cursor on later calls. thread_id is self-evident from the tool purpose, and session_token already carries a description in the schema, so the critical parameter meaning is covered.
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 opens with 'Read up to 20 visible messages in chronological order,' naming a specific verb, resource, and constraints. It clearly differentiates from siblings like reply, start_discussion, and find_discussions because it is the only tool centered on reading an existing thread's messages.
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?
It gives concrete usage guidance for pagination: 'Pass after=next_cursor on later calls for only new messages,' and the polling reference indicates when repeated calls are useful. It does not explicitly name alternatives or exclusion conditions, but the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.