detect_purpose_driftCompare original, current, and allowed purposes to detect data purpose drift across workflow steps and flag disallowed shifts like research to commercial.
Detect when data purpose drifts through a workflow (e.g. research → commercial).
| Name | Required | Description | Default |
|---|---|---|---|
| currentPurpose | Yes | ||
| allowedPurposes | Yes | ||
| originalPurpose | Yes | ||
| intermediateSteps | No |
Changes observed during successful MCP inspections.
v4.0.0Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falsev2.8.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds only the drift-direction concept and an illustrative example; it discloses nothing about how drift is judged, what counts as a violation, or how the four inputs interact.
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 front-loaded sentence with no filler and the example parenthetically attached. It is efficient, though the terseness is part of the under-specification problem rather than a virtue here.
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 three required parameters (including two arrays) and zero schema descriptions, the definition is too thin: it neither explains the parameters nor describes what a drift evaluation returns. Annotations cover the safety profile and there is no output schema, but the input semantics remain unaddressed.
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?
With schema description coverage at 0%, the description carries the full burden of explaining the four parameters, but it names none of them. The 'research → commercial' example loosely gestures at originalPurpose/currentPurpose, yet allowedPurposes and intermediateSteps are left entirely undefined in both schema and description.
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 and resource: detecting purpose drift through a workflow, with a concrete example (research → commercial). However, it does not differentiate from adjacent siblings like check_purpose_permitted or check_usage_permitted, which an agent might confuse with this detection role.
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 says what is detected but gives no when-to-use context, no prerequisites, and no indication of how it relates to the many sibling governance-check tools. The agent must infer the trigger scenario from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.