Search, cite and verify research papers on World Innovation, timestamped on Soneium.
Scored across 4 tools
Each tool maps to a distinct action on the same resource: discovery (search), retrieval of metadata (get), citation formatting (cite), and blockchain proof checking (verify). The only mild overlap is cite_paper vs get_paper, since both take a paper identifier and return paper-derived content, but the descriptions make the output difference clear.
All four tools follow a strict verb_noun snake_case pattern (cite_paper, get_paper, search_papers, verify_paper). Verb choice is precise and the plural/singular noun usage correctly signals collection vs single-item scope.
Four tools is lean but each earns its place: search, get, cite, and verify cover the distinct access modes of a published-paper registry with no filler or redundant entries. Nothing suggests a missing sibling tool at this scope.
The read-only lifecycle (discover → fetch → cite → verify provenance) is fully covered, which is appropriate for a published-archive server. Minor gaps: no explicit list/browse-all or pagination operation, and citation output is limited to APA/BibTeX, but agents can reach any paper via search_papers.
Get a ready-to-use citation for a World Innovation paper (APA-style text and BibTeX).
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already declares this as a safe read, so the bar is low, and the description adds useful behavioral context by naming the return formats (APA text + BibTeX). It does not say what happens with an unknown slug or whether one or both formats are always returned.
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 sentence, front-loaded with the verb and the output formats, with no filler. Every clause carries information.
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?
For a one-parameter read-only tool with no output schema, the description carries the return-value burden well by naming both formats; the remaining gap is the unexplained slug, which an agent may not know how to source.
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 single required 'slug' parameter has 0% schema description coverage and the description never explains what a slug is or how to obtain one; 'for a World Innovation paper' only loosely implies it identifies the paper. The description does not compensate for the schema gap.
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 ('Get') and resource ('citation') and the concrete output formats ('APA-style text and BibTeX'), scoped to World Innovation papers. It is clearly distinct from get_paper/search_papers/verify_paper by the word 'citation', though no sibling is named explicitly.
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?
Usage is only implied: 'Get a ready-to-use citation' tells the agent to call it when a formatted reference is needed, but it never says when to prefer get_paper vs cite_paper or states any preconditions such as the paper needing to exist. No exclusions or alternatives are given despite three siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get one World Innovation paper: title, author, abstract, keywords, publish date, SHA-256 fingerprint and blockchain proof.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Paper slug from search_papers |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already covers the safety profile, and the description adds genuine behavioral context by disclosing the returned payload (title, author, abstract, keywords, publish date, SHA-256 fingerprint, blockchain proof) in the absence of an output schema. It does not cover failure behavior for an unknown slug, which is the remaining gap.
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?
A single front-loaded sentence with the returned-field enumeration folded in; no wasted words and everything the agent needs is at the start.
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?
For a one-parameter read tool with readOnlyHint and no output schema, the description compensates well by enumerating the response fields. Only error/not-found behavior is left unaddressed.
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?
Only one parameter and schema description coverage is 100%, so the schema already explains that slug comes from search_papers. The description adds no further format or validation detail, making the baseline 3 correct.
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 and resource ('Get one World Innovation paper') and enumerates what a paper record contains, so the agent knows exactly what comes back. It implicitly distinguishes itself from search_papers by scoping to a single paper, but never names the sibling explicitly.
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?
Usage is only implied: 'one ... paper' suggests a detail fetch rather than a search, and the slug description in the schema ('Paper slug from search_papers') hints at the search-then-fetch flow. The description itself gives no when-to-use, prerequisites, or alternatives among cite_paper/verify_paper.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search published World Innovation research abstracts and white papers by topic or keyword. Returns titles, authors, short summaries and links.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Topic or keywords |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint already establishes this is a safe read, and the description adds useful return-shape detail (titles, authors, summaries, links) that annotations cannot convey. However it says nothing about result caps, relevance ordering, or what happens when a query matches nothing.
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 filler, with the search scope front-loaded before the return-shape sentence. Nothing here could be cut without losing information.
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?
With no output schema, the description helpfully enumerates the returned fields, so an agent knows what it will get back. The remaining gap is the undocumented limit/paging behavior, which matters for an agent deciding how many results to request.
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 coverage is only 50%: query is documented, but limit (default 8, max 20) has no schema description and no mention in the description. 'By topic or keyword' mildly reinforces query semantics but the description does not compensate for the undocumented limit 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?
States a specific verb (Search) and resource (published World Innovation research abstracts and white papers) with the discovery axis (topic or keyword). It implicitly contrasts with get_paper/cite_paper/verify_paper by framing this as discovery rather than retrieval, but never names a sibling explicitly.
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?
Usage is implied: use this to find papers, then presumably use get_paper to read one. No explicit when-to-use/when-not-to-use or pointer to the sibling tools that would complete the workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check whether a SHA-256 fingerprint (or a paper slug) matches a World Innovation paper anchored on the Soneium blockchain, and return its on-chain timestamp. The proof shows the exact text existed at that time; it does not show the ideas are correct or peer reviewed.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | No | ||
| sha256 | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already covers the safety profile, and the description adds useful semantics about what the returned timestamp proves and does not prove. It does not say how a mismatch is signaled, nor what happens with zero or both inputs (required parameters = 0), which are meaningful behavioral gaps for a lookup tool.
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 tightly written sentences, front-loaded with the action and its output, followed by a scope caveat. No filler.
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?
With no output schema, the description adequately states the return value (on-chain timestamp) and bounds the meaning of the proof. The main remaining gap is mismatch/error behavior and input-selection rules.
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 description coverage, the description carries the burden and does partially compensate: it defines both inputs ('SHA-256 fingerprint' and 'paper slug') and the 'or' relationship between them. It omits format details for slug, precedence when both are supplied, and the behavior when neither is given.
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 and resource: checks whether a SHA-256 fingerprint or paper slug matches an anchored paper and returns the on-chain timestamp. It is clearly a verification operation and implicitly distinct from retrieval siblings like get_paper, though it never names an alternative explicitly.
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 caveat that the proof shows existence at a time but not correctness or peer review gives the agent interpretive guidance for the result. However, there is no explicit when-to-use versus cite_paper, get_paper, or search_papers, and no statement about which input to supply.
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.
cite_paperget_papersearch_papersverify_paperAcademic papers, reference verification and research data for AI agents.
Academic paper search, scientific literature, citation analysis, arXiv & semantic related-work.
Search 220M+ scholarly papers with abstracts, DOIs, retraction flags and citation links.
Search 340M+ academic papers — citation graphs, semantic similarity, and AI literature reviews.
Add one secure layer between your agents and this server.
