Record the pedagogical decision actually implemented in a tutoring session, capturing rationale, strategy, and expected outcome for later replay and review.
Record the decision actually acted on, for later replay.
| Name | Required | Description | Default |
|---|---|---|---|
| node_id | No | ||
| rationale | No | ||
| request_id | No | ||
| session_id | Yes | ||
| trigger_event | No | ||
| selected_action | No | ||
| expected_outcome | No | ||
| selected_strategy | No |
Changes observed during successful MCP inspections.
v2.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing effects. It only says the tool records for replay, but does not say whether it appends to a log, has side effects, is idempotent, requires prior session state, or returns a confirmation. This is a significant gap for a mutating commit operation.
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 a clear verb, object, and purpose, and no filler. The key constraint ('actually acted on') is front-loaded, so an agent can quickly understand the tool's intent.
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 an 8-parameter, no-annotation, no-output-schema mutation tool, one sentence is insufficient. Missing context includes durability of the record, what 'replay' entails, whether related records must exist first, and what the response or side effects will be.
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%, and the description adds no parameter-level meaning beyond what the property names themselves imply. It does not explain which fields form a valid decision record, what node_id/request_id represent in this context, or how selected_action relates to selected_strategy; the description should compensate for the missing schema descriptions but does not.
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 action ('Record'), a specific object ('the decision actually acted on'), and a purpose ('for later replay'). The phrase 'actually acted on' distinguishes it from sibling tools that evaluate or retrieve decisions, such as evaluate_pedagogical_policy and get_decision_log.
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 wording implies this should be called after a decision has been executed, not for hypothetical or evaluated options, but it never names alternatives or states when to prefer a sibling tool. There is no explicit when/when-not guidance or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.