Propose an update for owner review; expected_version prevents lost updates.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Resource ID from a prior response. For memory use your stable note name, e.g. working-context. | |
| data | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | ||
| replayed | No | ||
| operation | No | ||
| truncated | No | ||
| next_cursor | No |
Changes observed during successful MCP inspections.
Input schema / properties / data / properties / body / descriptionPrevious value: -"Task-specific text the user intends to store for the selected audience; no full chat transcripts, credentials or restricted personal records. Non-empty, at most 20 KiB UTF-8 (replies/evidence at most 10 KiB)."New value: +"Task-specific text the user intends to store for the selected audience. Non-empty, at most 20 KiB UTF-8 (replies/evidence at most 10 KiB)."Input schema / properties / data / properties / body / descriptionPrevious value: -"Text to store. Non-empty, at most 20 KiB UTF-8 (replies/evidence at most 10 KiB)."New value: +"Task-specific text the user intends to store for the selected audience; no full chat transcripts, credentials or restricted personal records. Non-empty, at most 20 KiB UTF-8 (replies/evidence at most 10 KiB)."Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "description": "Structured result for propose_knowledge_update. Resource fields vary by detail, permissions and operation. Paginated results use items/next_cursor; operation-key replays use operation/replayed. Failures have error and the MCP result has isError=true. See get_help for this tool's contract.",
+ "properties": {
+ "error": {
+ "properties": {
+ "code": {
+ "type": "string"
+ },
+ "help": {
+ "type": "string"
+ },
+ "message": {
+ "type": "string"
+ },
+ "next_action": {
+ "type": "string"
+ },
+ "retry_after_seconds": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "code",
+ "message",
+ "next_action",
+ "help"
+ ],
+ "type": "object"
+ },
+ "next_cursor": {
+ "type": "string"
+ },
+ "operation": {
+ "type": "object"
+ },
+ "replayed": {
+ "type": "boolean"
+ },
+ "truncated": {
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+}Input schema / properties / data / properties / operation_keyAdded value: +{
+ "description": "Optional stable client key scoped to this agent for 30 days. Reuse identical payload after a timeout. Different payload conflicts. Retry returns compact operation receipt, not original body. Distinct from diagnostic request_id; existing create-space request_id remains required.",
+ "maxLength": 80,
+ "pattern": "^[a-z0-9]+(-[a-z0-9]+)*$",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds the concurrency mechanism (expected_version prevents lost updates, stale versions fail without overwriting is in the schema), which is useful context. The 'propose for owner review' phrasing sits slightly oddly against destructiveHint=true, but doesn't contradict it.
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 with no filler; the concurrency safeguard is front-loaded. Efficient and easy to scan.
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?
A nested-object tool with an output schema and rich schema-level parameter docs is mostly covered. However, for a destructive operation, the description gives no guidance on when proposing is appropriate versus alternatives, which is a real gap.
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 50%, but the schema itself carries rich per-field descriptions (sizes, version semantics, operation_key behavior). The description's prose adds the key expected_version concurrency meaning, reinforcing but not substantially extending the schema.
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 (propose), resource (knowledge update), and a distinctive mechanism (expected_version prevents lost updates). It's clearly distinct from create_knowledge_page and save_memory, though it doesn't name a sibling explicitly.
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?
'For owner review' implies an approval workflow, but there's no explicit when-to-use guidance, no exclusions, and no alternatives named. An agent must infer when to choose this over save_memory or create_knowledge_page.
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.