Check Crossref standard DOI revisions or supersession; preserve provenance, conflicts, UNKNOWN.
Scored across 1 tool
With only one tool in the set, there is no possibility of misselection between tools, and its purpose (a Crossref standard-type pre-action evidence gate) is stated unambiguously. The extensive negative-use clauses sharpen rather than blur its boundary, since there is nothing else to confuse it with.
The single tool name tovrek.resolve_current_state uses a clear namespace prefix plus a consistent verb_noun-style snake_case identifier. With one tool there is no competing convention to break the pattern, so the naming reads predictably.
The server exposes exactly one tool for what appears to be a deliberately narrow, single-purpose gate, so the count is not incoherent. However, a one-tool surface is inherently thin under this rubric, leaving no room for even closely related operations.
For a read-only evidence gate the resolve operation covers the core need, bundling provenance, conflict, and explicit-UNKNOWN handling, and mutation is intentionally out of scope. Minor gaps remain, such as no batch/multi-record resolution or separate retrieval of provenance after the fact.
Pre-action evidence gate for Crossref records whose record type is standard: determine what the currently available technical/industry-standard DOI metadata supports before an autonomous system cites, stores, publishes, ingests, or otherwise acts, while preserving provenance, conflicts, unresolved evidence, and explicit UNKNOWN. Use when a downstream action depends on a supported metadata fact for a Crossref standard-type DOI record and the record may be stale, incomplete, conflicting, or insufficient; when publication status, supersession, revision, adoption, approval date, designator, standards-body metadata, title, DOI, edition, or metadata surface must be checked before action; or when provenance and explicit UNKNOWN handling matter. Do not use for ordinary journal articles, citation validation, retraction checking, scholarly literature verification, or general multi-provider DOI resolution. Also do not use when raw Crossref metadata alone is sufficient, or to establish scientific truth, claim validity, legal or regulatory authority, open-ended literature search, historical reconstruction, unsupported identifier families, general fact verification, or mutation.
| Name | Required | Description | Default |
|---|---|---|---|
| as_of | No | Optional ISO-8601 date/timestamp. Omission is carried as a separate flag so the runtime may use the current materialised observation. | |
| entity | Yes | Exact Crossref standard-type DOI source identifier, for example crossref:doi:<DOI>. Ordinary journal-article DOI records are outside the current capability. | |
| context | Yes | Exact supported technical-standard metadata fact predicate whose current evidence-supported state must be checked. See the capability beacon supported_scope.predicates list. |
| Name | Required | Description |
|---|---|---|
| result | No | Evidence-backed resolver result preserving provenance, conflicts, unresolved evidence and explicit UNKNOWN. |
| retryable | No | |
| error_code | No | |
| profile_id | Yes | |
| reason_code | No | |
| capability_id | Yes | |
| admission_kind | No | Internal cost-bearing admission category; not a customer payment or charge. |
| correlation_id | Yes | |
| schema_version | Yes | |
| required_action | No | |
| resolver_version | Yes | |
| transport_version | Yes | |
| capability_version | Yes | |
| customer_charge_status | No | The free-machine profile does not charge the caller for this invocation. |
| resolver_schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover read-only and open-world hints, so the safety profile is established structurally. The description adds behavioral context beyond that: it preserves provenance, conflicts, unresolved evidence, and explicit UNKNOWN, and emphasizes pre-action evidence gating. It does not disclose rate limits, latency, or error behavior, but for a read-only resolver that is minor.
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 a single ~200-word sentence padded with enumerations and an exhaustive exclusion list. The core purpose and usage conditions are buried rather than front-loaded, and the structure forces the reader to parse one run-on clause chain to find them.
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?
An output schema exists, so return values need not be explained. The description covers scope, when/when-not, and behavior (provenance, UNKNOWN handling) sufficiently for an agent to decide and invoke correctly. The verbose phrasing is a readability problem rather than an information gap.
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%, so entity, context, and as_of are fully documented in the schema, including the crossref:doi:<DOI> format and the guidance to consult supported_scope.predicates. The description adds no parameter-level detail beyond that, so baseline 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-plus-resource: resolving current evidence-supported state for Crossref standard-type DOI records as a pre-action gate. It names concrete facets (publication status, supersession, designator, edition) that identify the resource precisely. It lacks sibling differentiation, but no siblings exist to confuse it with.
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?
Explicit when-to-use conditions are given (downstream action depends on a supported metadata fact, record may be stale/conflicting/insufficient) alongside an extensive when-not list (journal articles, citation validation, retraction checking, raw Crossref sufficiency, scientific truth, unsupported identifier families, mutation). Nothing is left to inference.
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.
tovrek.resolve_current_state2 fields changedOutput schema / properties / admission_kind / descriptionAdded value: +"Internal cost-bearing admission category; not a customer payment or charge."Output schema / properties / customer_charge_statusAdded value: +{
+ "const": "NO_CUSTOMER_CHARGE_FREE_PROFILE",
+ "description": "The free-machine profile does not charge the caller for this invocation.",
+ "type": "string"
+}tovrek.resolve_current_state2 fields changedInput schema / properties / context / descriptionPrevious value: -"Exact supported DOI metadata fact predicate whose current evidence-supported state must be checked."New value: +"Exact supported technical-standard metadata fact predicate whose current evidence-supported state must be checked. See the capability beacon supported_scope.predicates list."Input schema / properties / entity / descriptionPrevious value: -"Exact supported DOI source identifier, for example crossref:doi:<DOI>."New value: +"Exact Crossref standard-type DOI source identifier, for example crossref:doi:<DOI>. Ordinary journal-article DOI records are outside the current capability."tovrek.resolve_current_state1 field changedOutput schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": true,
+ "anyOf": [
+ {
+ "required": [
+ "admission_kind",
+ "result"
+ ]
+ },
+ {
+ "required": [
+ "error_code",
+ "retryable"
+ ]
+ }
+ ],
+ "description": "Structured TOVREK Current-State Resolver response. Successful calls contain admission_kind and result; bounded failures contain error_code and retryable.",
+ "properties": {
+ "admission_kind": {
+ "type": "string"
+ },
+ "capability_id": {
+ "type": "string"
+ },
+ "capability_version": {
+ "type": "string"
+ },
+ "correlation_id": {
+ "type": "string"
+ },
+ "error_code": {
+ "type": "string"
+ },
+ "profile_id": {
+ "type": "string"
+ },
+ "reason_code": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "required_action": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "resolver_schema_version": {
+ "type": "string"
+ },
+ "resolver_version": {
+ "type": "string"
+ },
+ "result": {
+ "description": "Evidence-backed resolver result preserving provenance, conflicts, unresolved evidence and explicit UNKNOWN.",
+ "type": "object"
+ },
+ "retryable": {
+ "type": "boolean"
+ },
+ "schema_version": {
+ "type": "string"
+ },
+ "transport_version": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "schema_version",
+ "profile_id",
+ "capability_id",
+ "capability_version",
+ "resolver_schema_version",
+ "resolver_version",
+ "transport_version",
+ "correlation_id"
+ ],
+ "type": "object"
+}tovrek.resolve_current_stateSource-tiered retraction and citation judgments for DOIs; abstains when evidence is thin.
Verify a DOI or find papers via Crossref metadata. $0.005/call via x402.
Check that a reference resolves; see what supports, refutes or cites a paper. CC0 graph, read-only.
Search and resolve Zenodo datasets, software, and publications by DOI; trace versions and funding.
Add one secure layer between your agents and this server.
