Records learned facts as subject-predicate-value entries in a bitemporal context graph, with optional evidence, idempotent retry keys, and proposed status for review.
Record what you learned (value: any JSON). scope tenant or global needs evidence; key: an idempotent retry; status="proposed": awaits review.
| Name | Required | Description | Default |
|---|---|---|---|
| by | No | ||
| key | No | ||
| task | No | ||
| scope | No | task | |
| value | Yes | ||
| detail | No | ack | |
| status | No | ||
| subject | Yes | ||
| evidence | No | ||
| predicate | Yes |
Changes observed during successful MCP inspections.
v0.34.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation idempotentHint=false directly contradicts the description's claim that 'key: an idempotent retry.' This is a serious inconsistency that could mislead an agent about retry safety. The description also does not clarify permissions, review effects, or what happens to existing annotations.
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?
It is short and front-loads the action, but the semicolon-separated fragments are cryptic rather than efficient. Some details earn their place, yet the lack of structure makes it harder to parse than a well-formed sentence.
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 10-parameter write tool with no output schema, the description is far from complete. It omits most parameter semantics, does not explain the write/review lifecycle beyond status='proposed,' and contains an idempotency contradiction that undermines trust in the definition.
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 0% across 10 parameters, so the description must compensate, but it explains only value, scope, key, and status. Critical parameters like subject, predicate, evidence, by, task, and detail are left undocumented, and required subject/predicate receive no semantic explanation.
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 says 'Record what you learned,' which gives a verb but an ambiguous resource; it does not clarify that this stores an annotation/knowledge claim, nor does it distinguish the tool from siblings like context, history, search, or related. The parenthetical '(value: any JSON)' hints at structured storage but leaves the core purpose vague.
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 gives some conditional usage rules: tenant/global scopes require evidence, key enables idempotent retries, and status 'proposed' awaits review. However, it never states when to use annotate versus alternatives such as context or history, nor does it clearly mark when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.