Verifies the entire SHA-256 hash chain integrity for a domain. Performs O(n) sequential verification of all Decision Proof Units and reports the first broken index if tampering is detected.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | The domain to verify (e.g. rehab_care, market, edu) | |
| toIndex | No | End verification at this chain index | |
| batchSize | No | Number of DPUs to process per batch | |
| fromIndex | No | Start verification from this chain index |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden. It discloses algorithmic behavior (O(n) sequential verification) and output behavior (reports first broken index). However, it does not explicitly state whether the operation is read-only, whether it requires special permissions, or how failures like a nonexistent domain are handled.
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 focused sentences with no filler. It front-loads the core function and adds the most important behavioral nuance (O(n) complexity and broken-index reporting) in a compact way.
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 description explains the main verification behavior and one key output behavior, but no output schema is provided. It does not describe the full success return shape, what happens when no tampering is detected, or how the optional fromIndex, toIndex, and batchSize parameters affect verification. The core workflow is understandable, but details remain unclear for an agent.
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 schema has 100% parameter coverage, so each of the four parameters already has descriptive text. The description adds little about parameters, only implicitly tying 'domain' to the verification target. This meets the baseline for well-documented schemas but provides no additional semantic value beyond the schema.
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 clearly states the tool performs SHA-256 hash chain integrity verification for a specific domain, with an explicit scope of 'entire chain' and 'all Decision Proof Units.' This goes beyond a generic 'verify' and distinguishes the tool from sibling tools like proof_get or proof_report.
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 clearly conveys when to use the tool: when full-chain hash integrity verification is needed. It provides concrete details like O(n) sequential verification. However, it does not explicitly mention alternatives or when not to use the tool, leaving no exclusions or sibling comparisons.
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.
