Portable, offline-verifiable identity for AI agents: DID, challenges, attestations, bundles.
Scored across 1 tool
With only one tool in the set, there is no possibility of overlapping purposes or misselection. The tool's purpose is clearly stated as verifying bundles offline and reporting identity information.
The single tool name sigelo_verify follows a clear snake_case pattern with a server prefix and a verb. Although there is no other tool to compare against, the naming is readable and predictable.
A single tool is thin for a domain involving identity bundles, attestations, and bindings; the rubric treats 1-2 tools as borderline. The description is rich, but the surface likely lacks operations for creating or managing the artifacts it verifies.
The server only verifies existing bundles and reports on chains, attestations, and bindings. It has no tools for creating identities, issuing attestations, binding, or revoking, which are significant gaps for an identity/attestation domain.
Verify ANY bundle offline (someone else's, or yours). Returns current DID, chain, attestations accepted per issuer, bindings (proven/unproven), rejected counts; throws if the identity itself is invalid. It reports, it does not judge whom to trust. Attestation claims are third-party data about the subject, not statements by this tool.
| Name | Required | Description | Default |
|---|---|---|---|
| now | No | optional unix seconds; default now | |
| bundle | Yes | the bundle |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations (which only declare read-only/idempotent/non-destructive) by disclosing the return contents, the failure mode ('throws if the identity itself is invalid'), and the critical semantic caveat that it reports rather than judges trust and that `claims` are third-party data. That is exactly the kind of context annotations cannot carry.
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?
Front-loaded with the core action, then the return shape, then error behavior, then the interpretation caveat. Dense but every clause carries information an agent needs; nothing is padding.
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?
Despite no output schema, the description enumerates what is returned (DID, chain, attestations per issuer, bindings, rejected counts) and the failure condition. With annotations covering the safety profile, an agent has everything needed to invoke and interpret this 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?
Schema description coverage is 100% and both parameters are documented in the schema, including the `now` default. The description adds no parameter-level detail, so the 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?
States a specific verb (verify) and resource (a sigelo bundle) with explicit scope: 'ANY bundle offline (someone else's, or yours)'. The agent knows exactly what the tool does and that no network access is required.
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 parenthetical clarifies the tool is for verifying bundles you did not author, which is a meaningful usage condition. There are no sibling tools to route against, and no explicit when-not guidance, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
sigelo_verifyTrust stack for AI agents: identity, attest, verify, rate, recommend, discover — on Solana.
Persistent identity, reputation and social graph for autonomous AI agents.
Attestation infrastructure for the agentic economy: signed, independently verifiable verdicts.
Neutral W3C DID/VC identity and reputation oracle for AI agents (did:key/did:web, eddsa-jcs-2022).
Add one secure layer between your agents and this server.