Onchain Diary exposes its full knowledge base — 96 Web3 security articles and 220 glossary terms, in English and Chinese — through the Model Context Protocol. Any MCP-capable assistant can search it and read complete articles without scraping HTML.
Scored across 4 tools
Each tool serves a clearly distinct purpose: listing content, reading an article, reading a glossary term, and searching across content. There is no overlap or ambiguity between them, even for similar operations like reading an article vs. reading a glossary.
All tool names follow a consistent snake_case verb_noun pattern (list_content, read_article, read_glossary, search). While 'search' is a single verb, it is a common exception and the overall pattern is uniform and predictable.
Four tools is a well-scoped set for a content access server. Each tool covers a distinct access mode (list, read, search) without redundant or unnecessary additions, making the surface compact yet functional.
The tool surface fully covers the server's purpose: browsing the table of contents, retrieving articles and glossary terms, and searching across both languages. There are no obvious gaps in the core workflow of discovery and reading.
List the table of contents: all articles (grouped by language, newest first) or all glossary terms (grouped by category).
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Which catalog to list (default: articles) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of behavioral disclosure. It discloses grouping and ordering behavior for articles and glossary terms, which is useful and non-obvious. It does not describe a default type or return format, but the omitted details are minor for a simple listing operation.
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 well-formed sentence that front-loads the core action and then specifies the two modes. Every phrase adds value, with no redundant or vague 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?
For a low-complexity tool with one optional enum parameter, the description is largely complete: it explains what is listed, how results are ordered, and how they are grouped. It could additionally mention the default value, but that is already covered by the input schema.
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 already fully documents the single optional parameter, including its enum values and default. The description adds contextual meaning for the two values but does not need to compensate for any schema gap, so the baseline score of 3 is appropriate.
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 names a clear action ('List the table of contents') and defines the exact scope: all articles grouped by language and ordered newest first, or glossary terms grouped by category. This is specific enough to distinguish the tool from siblings like read_article, read_glossary, and search.
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 makes the browsing/overview use case clear by saying it lists the table of contents rather than reading a single item or searching. It does not explicitly name alternatives or exclusions, but the intended usage is evident from the wording.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the full markdown text of one article. Accepts the article slug (e.g. "wallet-drainer-anatomy") or its site path (/articles/... or /zh/articles/...).
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Article slug or path |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It clearly identifies this as a read operation returning markdown text and discloses the accepted path variants. It doesn't cover error behavior, but for a simple read tool the core behavior is transparent.
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, front-loaded with action and output, followed by concise input examples. Every phrase contributes.
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 single-parameter read tool with no output schema, the description states what is returned and what input is accepted. It omits error/not-found behavior and alternative-tool routing, but those are minor gaps for this level of complexity.
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 already documents the single slug parameter at 100% coverage, so the baseline is 3. The description adds value with a concrete slug example and the exact path formats (/articles/... and /zh/articles/...), going beyond the schema's one-line description.
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 (read) and resource (article), and adds the output format (full markdown text). It doesn't explicitly differentiate from siblings like read_glossary or list_content, so it stops short of a 5.
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 implies when to use it—when you need the full markdown of one article—and provides accepted input forms. It gives no explicit guidance about when not to use it or how it compares to list_content, read_glossary, or search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read one glossary term: full English definition plus the Chinese translation (译名 + 中文定义). Accepts the term slug (e.g. "address-poisoning") or its site path.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Glossary term slug or path |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses the read-only action, the accepted input forms, and the output composition. It does not describe not-found or error behavior, which is a minor gap for a simple read 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 concise sentences convey the action, output content, and accepted input format with no redundancy. The most essential information is front-loaded.
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 single-parameter tool with no output schema, the description is nearly complete: it defines the input format and the return contents. It lacks error-handling details, but that does not prevent an agent from selecting and invoking the tool correctly.
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 100%, so the baseline is 3. The description adds value by giving a concrete slug example ('address-poisoning') and clarifying that a site path is also accepted, which goes beyond the schema's brief 'Glossary term slug or path'.
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 reads one glossary term and specifies the returned content: full English definition plus Chinese translation. It is specific about the resource, but it does not explicitly differentiate this tool from siblings like read_article or list_content.
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 provides clear context: use when you need a single glossary term by slug or site path. It does not explicitly state exclusions or name alternative tools, but the scope is evident and unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Onchain Diary articles and glossary terms (Web3 security education, EN/ZH). Returns the top matches with title, URL and short description. Use this first to discover relevant content.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Optional: restrict results to one language | |
| type | No | Optional: restrict results to one content type | |
| query | Yes | Search keywords, e.g. "wallet drainer", "地址投毒", "permit2 phishing" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description carries the full behavioral burden and does a solid job: it states that the tool returns top matches with title, URL, and short description. It also adds useful context about the content domain and language coverage that goes beyond the schema.
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?
Three short sentences, each earning its place: the first states what the tool searches, the second describes the return format, and the third gives usage priority. It is front-loaded and free of fluff.
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 simple search tool with three documented parameters and no output schema, the description is sufficiently complete. It explains the resource, the return fields, and the intended first-use role. It could add explicit notes about limits (e.g., 'top' count) but nothing critical is missing.
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 the baseline of 3 applies. The description does not add parameter-level detail beyond what the schema already provides, but that is acceptable because the schema itself includes examples and clear descriptions.
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 opens with a specific verb and resource ('Search Onchain Diary articles and glossary terms'), making the tool's function immediately obvious. It also names the content covered (Web3 security education, EN/ZH) and the return shape, which helps differentiate it from the sibling tools (list_content, read_article, read_glossary).
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 'Use this first to discover relevant content' gives clear strategic guidance for when this tool is appropriate in a workflow. It does not explicitly name alternative tools or exclusion conditions, but the intent is strong enough for an agent to route correctly.
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.