Retrieves a Decision Proof Unit by ID with full details including hash chain position, AI involvement, human control, evidence level, and compliance information.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The DPU ID to retrieve |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It correctly indicates a retrieval operation and lists the content fields, but it does not disclose behavior around missing IDs, permissions, side effects, or response format. It is acceptable but not thorough.
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?
One concise, front-loaded sentence uses a single specific verb and a compact list of relevant detail categories. There is zero wasted text and the structure is easy to scan.
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 is low-complexity: a single required string parameter and no output schema. The description adequately communicates the purpose and the nature of the returned data. Omitting error handling or output container details is a minor gap, but the description is sufficient for a simple lookup tool.
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?
The only parameter id already has a schema description ('The DPU ID to retrieve'), and the tool description adds no additional format, source, or constraint details. Since schema description coverage is 100%, baseline of 3 applies.
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 verb ('Retrieves') and resource ('Decision Proof Unit by ID'), and enumerates exactly what kind of details are returned. This clearly distinguishes it from siblings like proof_verify or proof_chain_verify, which focus on verification and chain checks rather than plain retrieval.
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?
No guidance is provided on when to use this rather than a sibling such as proof_verify, proof_public_verify, or proof_report. The broad use case (retrieve a DPU by ID) is clear, but there are no exclusions or explicit alternative references.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly distinct (record, get, export, report, chain verify), but proof_verify and proof_public_verify both verify cryptographic integrity with overlapping semantics. The descriptions clarify the auth and chain-link differences, but an agent could still confuse them.
All tools follow a strict 'proof_' prefix with a verb action (get, record, verify, export, report, chain_verify, public_verify). The pattern is consistent, snake_case throughout, and predictable.
With 7 tools covering proof recording, retrieval, verification, export, and reporting, the server is well-scoped for its purpose. No redundancy or bloat, and each tool serves a clear function.
The tool surface covers the full lifecycle of proof management: record (create), get (read), verify (check integrity), export (format), and report (human-readable output). A list operation is missing, but it's not critical for the domain's core workflows.
