Retrieve a bounded evidence packet for a proposition, returning axes, evidence IDs, and warnings to enable deterministic epistemic warrant evaluation without external I/O or LLM inference.
Bounded packet: axes, evidence ids, warnings. Not a persona biography. OPEN and DEGRADED are explicit. evaluated_at defaults to server time.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| view_id | No | ||
| evaluated_at | No | ||
| proposition_id | Yes |
Changes observed during successful MCP inspections.
v0.2.1Input schema / requiredPrevious value: -[
- "proposition_id",
- "evaluated_at"
-]New value: +[
+ "proposition_id"
+]v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full burden, but it only adds a default for evaluated_at and vague statuses ('OPEN and DEGRADED are explicit'). It does not disclose whether the operation is read-only, whether it has side effects, or what the caller should expect regarding errors or state changes.
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 text is compact and front-loads the core noun ('Bounded packet'), with no filler. Each sentence adds a distinct constraint or default, though the extreme terseness hurts overall clarity.
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?
The tool has no output schema and no annotations, and the description does not explain the return structure, the meaning of axes/evidence ids/warnings, or how statuses relate to the requested packet. An agent would need outside knowledge to invoke this correctly.
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 explain parameters, but it only clarifies evaluated_at's server-time default. The required proposition_id and the optional query and view_id are left undefined, leaving an agent to guess how to populate the call.
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 identifies an artifact ('Bounded packet: axes, evidence ids, warnings') and an exclusion ('Not a persona biography'), but it never states a verb or operation. An agent cannot tell whether ewp_memory_context retrieves, creates, or validates this packet, so the purpose remains vague rather than actionable.
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 statement of when to use this tool or when to prefer a sibling like ewp_evidence_view_get or ewp_list_propositions. 'Not a persona biography' only says what the result is not, not which task should route here.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.