thread_link
Deprecated, works until 2026-11-10: use node_link.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | ||
| key | No | ||
| why | No | ||
| from | Yes | ||
| kind | No | ||
| remove | No |
Deprecated, works until 2026-11-10: use node_link.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | ||
| key | No | ||
| why | No | ||
| from | Yes | ||
| kind | No | ||
| remove | No |
Changes observed during successful MCP inspections.
Input schema / properties / key / descriptionRemoved value: -"agent key, when not signed in to an account"Input schema / properties / kindAdded value: +{
+ "enum": [
+ "relates",
+ "blocks",
+ "duplicates",
+ "fixed-by",
+ "part-of",
+ "answers",
+ "supersedes"
+ ],
+ "type": "string"
+}Input schema / properties / why / descriptionRemoved value: -"one line, at most 200 characters"Input schema / properties / key / descriptionAdded value: +"agent key, when not signed in to an account"Input schema / properties / kindRemoved value: -{
- "enum": [
- "relates",
- "blocks",
- "duplicates",
- "fixed-by",
- "part-of",
- "answers",
- "supersedes"
- ],
- "type": "string"
-}Input schema / properties / why / descriptionAdded value: +"one line, at most 200 characters"Input schema / properties / key / descriptionRemoved value: -"agent key, when not signed in to an account"Input schema / properties / kindAdded value: +{
+ "enum": [
+ "relates",
+ "blocks",
+ "duplicates",
+ "fixed-by",
+ "part-of",
+ "answers",
+ "supersedes"
+ ],
+ "type": "string"
+}Input schema / properties / why / descriptionRemoved value: -"one line, at most 200 characters"Input schema / properties / key / descriptionAdded value: +"agent key, when not signed in to an account"Input schema / properties / kindRemoved value: -{
- "enum": [
- "relates",
- "blocks",
- "duplicates",
- "fixed-by",
- "part-of",
- "answers",
- "supersedes"
- ],
- "type": "string"
-}Input schema / properties / why / descriptionAdded value: +"one line, at most 200 characters"Input schema / properties / kindAdded value: +{
+ "enum": [
+ "relates",
+ "blocks",
+ "duplicates",
+ "fixed-by",
+ "part-of",
+ "answers",
+ "supersedes"
+ ],
+ "type": "string"
+}Input schema / properties / key / descriptionRemoved value: -"agent key, when not signed in to an account"Input schema / properties / why / descriptionRemoved value: -"one line, at most 200 characters"Input schema / properties / key / descriptionAdded value: +"agent key, when not signed in to an account"Input schema / properties / why / descriptionAdded value: +"one line, at most 200 characters"Input schema / properties / key / descriptionRemoved value: -"agent key, when not signed in to an account"Input schema / properties / why / descriptionRemoved value: -"one line, at most 200 characters"Input schema / properties / key / descriptionAdded value: +"agent key, when not signed in to an account"Input schema / properties / why / descriptionAdded value: +"one line, at most 200 characters"Input schema / properties / from / propertiesRemoved value: -nullInput schema / properties / key / propertiesRemoved value: -nullInput schema / properties / remove / propertiesRemoved value: -nullInput schema / properties / to / propertiesRemoved value: -nullInput schema / properties / why / propertiesRemoved value: -nullInput schema / properties / from / propertiesAdded value: +nullInput schema / properties / key / descriptionRemoved value: -"agent key, when not signed in to an account"Input schema / properties / key / propertiesAdded value: +nullInput schema / properties / remove / propertiesAdded value: +nullInput schema / properties / to / propertiesAdded value: +nullInput schema / properties / why / descriptionRemoved value: -"one line, at most 200 characters"Input schema / properties / why / propertiesAdded value: +nullDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare mutation, open-world, non-idempotent, non-destructive behavior, so the description only adds the deprecation timeline. It discloses nothing about what a link creation actually does, what 'remove' does, or whether the operation is reversible.
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?
A single sentence with zero waste, and the deprecation notice plus deadline are front-loaded.
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 legacy mutation tool with six undocumented parameters and no output schema, the description only covers migration routing. An agent could avoid the tool but could not call it correctly if it needed to before the cutoff.
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?
Six parameters with 0% schema description coverage and the description supplies no parameter meaning at all. Non-obvious semantics like the 'kind' enum values and the 'remove' boolean are left entirely 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 never states what the tool does. It only says it is deprecated and points at node_link, so an agent must infer the purpose (linking threads/nodes) from the name and the replacement tool.
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 names the exact alternative (node_link) and a concrete cutoff date (2026-11-10). This is a clear when-not-to-use instruction, though it does not say under what circumstances, if any, the legacy tool should still be called.
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.