Evaluate an EvidenceView at a given time to get the five normative axes for epistemic warrant, without persisting the result.
Evaluate an EvidenceView (inline or stored) at evaluated_at. Returns the five normative axes. Does not persist warrant.
| Name | Required | Description | Default |
|---|---|---|---|
| view | No | ||
| view_id | No | ||
| policy_id | No | ||
| evaluated_at | Yes | ||
| policy_version | No | ||
| proposition_id | No |
Changes observed during successful MCP inspections.
v0.2.0Does 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 add useful non-obvious information: the tool returns five normative axes and does not persist the warrant. But it omits other behavioral details such as prerequisites, error conditions, whether it requires a stored view vs inline object, and what happens with conflicting parameters.
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 short sentences with no filler. The core action is front-loaded, the 'does not persist' note is a purposeful behavioral clarification, and every sentence earns its place.
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?
Given six parameters, 0% schema coverage, no output schema, and no annotations, this description is too sparse to fully support correct invocation. It establishes the main intent and the non-persistence side effect, but leaves most parameter semantics and the expected response shape underspecified.
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%, so the description must compensate. It partially does by distinguishing 'inline or stored' EvidenceViews, which roughly maps to view vs view_id, and by tying evaluated_at to the evaluation time. However, policy_id, policy_version, proposition_id, and the relationship between view and view_id are left completely unexplained.
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 states a specific operation: evaluate an EvidenceView at a point in time, and names the result ('five normative axes'). 'Does not persist warrant' helps separate it from persistence tools. However, it does not explain what the 'five normative axes' are or how this tool relates to siblings like ewp_check_record or ewp_may_act.
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?
There is no explicit when-to-use or when-not-to-use guidance. The only signal is 'Does not persist warrant,' which hints that this tool is for evaluation rather than storage, but no alternative tool is named and no selection criteria are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.