Persist a note under the given session code. Session-gated — bootstrap_session first. Callers sharing the code share the memory.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | ||
| from | No | ||
| tags | No | ||
| text | Yes | ||
| session_token | No | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
Changes observed during successful MCP inspections.
Input schema / properties / session_tokenAdded value: +{
+ "description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header.",
+ "type": "string"
+}Input schema / properties / code / descriptionRemoved value: -"Session code that owns this memory (lets a future agent retrieve it via recall)."Input schema / properties / from / descriptionRemoved value: -"Optional: agent identity."Input schema / properties / tags / descriptionRemoved value: -"Optional: tags for filtering on recall."Input schema / properties / text / descriptionRemoved value: -"What to remember. Plain text, max 8000 chars."Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "content": {
+ "items": {
+ "properties": {
+ "text": {
+ "type": "string"
+ },
+ "type": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It does reveal that the operation is session-gated and that memory is shared among code holders, which adds context beyond the schema. However, it leaves out important behaviors such as whether the note is appended or overwritten, what happens if the code is invalid, or any authentication requirements beyond the initial bootstrap.
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?
The description is two concise sentences with no redundant words. The main action is front-loaded, and the session-gating constraint is stated immediately after the purpose.
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 tool with 5 parameters, 2 required, and no output schema, the description is too sparse. It does not mention what the tool returns, how parameters like 'from' and 'tags' are used, or any error conditions. The agent is left without enough context to confidently invoke the tool correctly in all cases.
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 20% (only 'session_token' has a description). The tool description connects 'session code' to the 'code' parameter and 'note' to 'text', but it does not explain the semantics of 'from' or 'tags'. This is insufficient compensation for the low schema coverage, leaving the agent to guess about those parameters.
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 uses a specific verb ('persist') and resource ('note') tied to a 'session code', clearly distinguishing this from sibling tools like 'recall' (which presumably reads notes). It also explicitly notes session-gating, making the operation's scope unambiguous.
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 gives a clear precondition ('bootstrap_session first') and a usage context ('Callers sharing the code share the memory'), implying when to use the tool. However, it does not explicitly mention when not to use it or name alternative tools.
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.