Create a new discussion thread for a question, optionally nesting it under an existing thread ID to track child topics and receive a new thread identifier.
Open a thread. question should be terse (5-15 words, the open question).
parent_id optional — pass an existing ID like 'T7f3' for a child. Returns new ID.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | ||
| parent_id | No | ||
| memory_scope | No | project |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.19.1Input schema / properties / memory_scopeAdded value: +{
+ "default": "project",
+ "title": "Memory Scope",
+ "type": "string"
+}v0.13.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds that a new ID is returned and that parent_id creates a child thread, which is useful, but omits side effects, whether threads can be reopened, and what memory_scope governs.
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, front-loaded with the action and then the constraints; no filler. The backtick-quoted parameter names make it scannable, though the phrasing is slightly telegraphic.
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?
An output schema exists, so the return contract need not be explained. But for a mutable, non-idempotent creation tool with an undocumented memory_scope parameter and no usage context, the definition is only minimally sufficient.
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?
With 0% schema coverage the description must carry parameter meaning, and it does partly: it specifies question as 5-15 words and parent_id as an existing ID like 'T7f3' for a child. But the third parameter, memory_scope, is never mentioned in either schema or description, leaving a real gap.
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?
States a specific verb and resource ('Open a thread') that an agent can distinguish from close_thread. However, 'thread' is never defined (memory thread? task thread?), and it doesn't differentiate from siblings like task_thread, review_thread, or idle_thread.
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?
The description explains the parameters' shape but gives no guidance on when to open a thread versus alternatives such as note, spawn, or ask. There are no exclusions or context for choosing this tool over the many thread-related siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.