proofrelay.recommend_checkpointChoose the next public-safe GENESIS checkpoint for a paid, material, or relied-upon agent workflow. Submit normalized context only; the tool returns reason codes without protected routing internals.
| Name | Required | Description | Default |
|---|---|---|---|
| workflow_context | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations (readOnlyHint=true, idempotentHint=true) already establish this is a safe read operation. The description adds meaningful behavioral context beyond this: 'returns reason codes without protected routing internals' clarifies the privacy boundary of the output, and 'public-safe' sets expectations about what the tool will filter for. No contradiction with annotations.
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?
Two sentences, zero waste. The first sentence front-loads the core action and scope; the second covers the privacy model. Every word earns its place, covering what, when, and output characteristics in breakneck efficiency.
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 an output schema exists, explaining returns would be redundant, and the annotations already provide safety context. However, with 26 sibling tools—several of which (e.g., build_bundle_draft, verify_bundle) overlap thematically with checkpoint/evidence concepts—the description should clarify where 'GENESIS checkpoint' fits relative to those alternatives. The undefined domain term and missing ecosystem positioning keep this from being complete for a nested, zero-coverage parameter.
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 0% schema coverage and a nested workflow_context object containing 12+ undocumented fields, the description must compensate—but 'Submit normalized context only' is the sole hint about parameter semantics. While field names are self-descriptive (e.g., payment_context_present), the description neither explains normalization requirements, field semantics, nor constraints, leaving a significant documentation gap for such a rich parameter.
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 uses a specific verb-resource pairing ('Choose the next... GENESIS checkpoint') with strong scope qualifiers ('public-safe,' 'paid, material, or relied-upon agent workflow') that clearly delimit the tool's domain. It distinguishes itself from siblings by implying a classification/eligibility role rather than an action tool, though the term 'GENESIS' remains an undefined domain term.
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 phrase 'for a paid, material, or relied-upon agent workflow' provides clear context for when to invoke the tool. 'Submit normalized context only' gives input guidance. However, no sibling alternatives are named and there is no explicit when-not-to-use guidance, which would have made this a 5 given the large sibling ecosystem.
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.
All 26 tools have distinct names that clearly indicate their purpose (e.g., adapt_agent_identity_evidence vs. build_audit_pack_manifest). No two tools have overlapping or ambiguous functions, even though some share similar verbs; the nouns and description contexts differentiate them effectively.
The tool names follow a uniform convention: all start with 'proofrelay.' and use lowercase verb_noun with underscores (e.g., proofrelay.build_bundle_draft, proofrelay.verify_signed_attestation). There is no mixing of camelCase, across the entire set.
The server exposes 26 tools, which exceeds the 'borderline' range of 16–25 and falls into the 'too many' category (>25). While the tools cover a broad domain (evidence verification, risk scanning, etc.), the large number might overwhelm agents and suggests that some tools could be merged or the scope narrowed.
The tool set covers a comprehensive range of operations—adapting, building, verifying, scanning, recommending, and summarizing—across multiple subdomains (identity, payment, audit, etc.). Minor gaps exist, such as missing tools for updating or deleting evidence, but overall the surface appears very complete for the described functionality.