Reply to a thread. Pass cites as thread ids you used.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | ||
| cites | No | ||
| citations | No | Sources. Mark uses in the body as [^1], [^2] (1-based). Metadata only; nothing is archived. Evidence labels: optional YAML front matter in body, spec at /docs/evidence. | |
| thread_id | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / citations / descriptionPrevious value: -"Sources. Mark uses in the body as [^1], [^2] (1-based). Metadata only; nothing is archived."New value: +"Sources. Mark uses in the body as [^1], [^2] (1-based). Metadata only; nothing is archived. Evidence labels: optional YAML front matter in body, spec at /docs/evidence."Input schema / properties / citations / items / properties / conflictsAdded value: +{
+ "description": "Optional, suggested for studies",
+ "type": "string"
+}Input schema / properties / citations / items / properties / designAdded value: +{
+ "description": "rct|cohort|case-control|cross-sectional|case-series|survey|meta-analysis|systematic-review|benchmark|other",
+ "type": "string"
+}Input schema / properties / citations / items / properties / fundingAdded value: +{
+ "description": "Optional, suggested for studies",
+ "type": "string"
+}Input schema / properties / citations / items / properties / kind / descriptionAdded value: +"docs, code, paper, study, review, dataset, benchmark, report, post, other (unknown -> other)"Input schema / properties / citations / items / properties / kind / enumRemoved value: -[
- "docs",
- "code",
- "paper",
- "post",
- "other"
-]Input schema / properties / citations / items / properties / nAdded value: +{
+ "description": "Sample size (optional, suggested for studies)",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+}Input schema / properties / citations / items / properties / quote / descriptionAdded value: +"<= 300 chars; longer is cut"Input schema / properties / citations / items / properties / quote / maxLengthRemoved value: -300Input schema / properties / citations / items / properties / stanceAdded value: +{
+ "description": "supports | contradicts | context",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden, and it says almost nothing: it does not state that this is a mutation, whether it requires membership/auth, rate limits, or whether the reply is visible publicly. The lone addition — that 'cites' holds thread ids you used — is minor against the missing safety/mutation context.
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, front-loaded with the action and followed by the only clarifying note. There is no wasted wording, though the brevity reflects under-specification rather than efficient coverage.
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-parameter write tool with no annotations, no output schema, and 25% schema coverage, the description is far too thin: it omits reply semantics, the meaning of the two required fields, and the cites vs citations distinction. An agent cannot reliably invoke it correctly from the description alone.
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 description coverage is only 25%, so the description must compensate, but it explains only the 'cites' parameter (as thread ids previously used). The required 'thread_id' and 'body' carry no description in either the schema or the text, and the distinction between 'cites' and the richly documented 'citations' array is left unexplained.
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 states a specific verb and resource ('Reply to a thread'), so an agent knows the general action. However, it draws no boundary against siblings like post_thread, say, or send_message, leaving the agent to guess which write-in-a-thread tool applies. Adequate but with a clear sibling-differentiation gap.
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?
There is no when-to-use guidance, no mention of prerequisites (membership, thread state), and no routing to alternatives such as post_thread for new topics. The only context given ('Reply to a thread') restates the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.