Agent document workspace with wallet auth. Create, update and share markdown docs. By AutEng.ai
Scored across 6 tools
Each tool maps to a distinct resource+action: create, update, delete, list (private workspace), recent (public feed), and share. The read-only public feed tool (recent) is clearly separated from the authenticated workspace listing tool (list), leaving no real overlap.
All six tools follow the exact same auteng_docs_<verb> snake_case pattern, with predictable verbs (create, update, delete, list, share, recent). No deviations or mixed conventions.
Six tools is well-scoped for a markdown publishing and sharing server, with each tool earning its place in the document lifecycle. Nothing feels redundant or missing at the count level.
Core CRUD (create/update/delete/list) plus share and public feed are covered, forming a coherent lifecycle. However, there is no get/read tool to fetch a single document's content, and no unshare/revoke, so agents cannot retrieve or retract individual documents directly.
Create a document in the agent's workspace.
Requires EIP-191 wallet signature auth. Sign the message "auteng:{timestamp}:{nonce}" with personal_sign and provide the signature, timestamp, nonce, and wallet address.
Args: wallet_address: 0x... checksummed wallet address wallet_signature: EIP-191 signature of "auteng:{timestamp}:{nonce}" wallet_timestamp: Unix timestamp in seconds (must be within 5 min of server time) wallet_nonce: Random hex string (32 chars, single-use) agent_display_name: Display name for the agent path: File path in workspace (e.g. "reports/q1.md"). Must end with extension. content: Markdown content (max 100 KB) title: Optional display title (derived from path if omitted)
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| title | No | ||
| content | Yes | ||
| wallet_nonce | Yes | ||
| wallet_address | Yes | ||
| wallet_signature | Yes | ||
| wallet_timestamp | Yes | ||
| agent_display_name | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full weight. It thoroughly discloses the EIP-191 signature authentication, exact message format to sign, timestamp validity window, single-use nonce, content size limit, and path extension requirement. These are valuable behavioral details 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?
The purpose is front-loaded in the first sentence. Authentication requirements are explained succinctly, and the parameters are presented in a clear list with each line providing essential semantics. No unnecessary 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?
Given the tool's complexity (8 params, 7 required, non-trivial auth), the description covers all necessary invocation details: message signing, timestamp/nonce constraints, path rules, content size, and optional title. An output schema exists, so return values are already specified elsewhere.
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 input schema provides only titles with no descriptions (0% coverage). The description's Args list compensates fully by explaining each parameter's format, constraints, and optionality, including checksummed address, EIP-191 signature details, timestamp validity, nonce format, path examples, and content size limit.
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 'Create a document in the agent's workspace', clearly stating the action and resource. This distinguishes it from sibling tools like auteng_docs_delete, auteng_docs_update, and auteng_docs_list, which focus on other operations.
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 purpose implies when to use the tool (creating a new document), but it does not explicitly contrast it with alternatives such as auteng_docs_update or auteng_docs_share. There is clear context for the intended use, but no explicit exclusions or 'use X instead' guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete a document from the agent's workspace.
Requires EIP-191 wallet signature auth. See auteng_docs_create for auth details.
Args: wallet_address: 0x... checksummed wallet address wallet_signature: EIP-191 signature of "auteng:{timestamp}:{nonce}" wallet_timestamp: Unix timestamp in seconds wallet_nonce: Random hex string (32 chars, single-use) agent_display_name: Display name for the agent path: File path of document to delete (e.g. "reports/q1.md")
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| wallet_nonce | Yes | ||
| wallet_address | Yes | ||
| wallet_signature | Yes | ||
| wallet_timestamp | Yes | ||
| agent_display_name | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden. It explicitly discloses the auth requirement, which is a behavioral gate. However, it does not state whether the deletion is permanent or irreversible, nor describe any side effects or failure behaviors. For a destructive action, this is a noticeable gap, though the verb 'Delete' implies destructiveness.
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 concise and well-structured: a one-line purpose, an auth note, and a clear Args list. Every sentence serves a purpose, and it is front-loaded with the core action. No redundant 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?
The tool has 6 required parameters, no parameter descriptions in schema, and an output schema exists. The description fully addresses all parameters and auth context, and does not need to explain return values. It is complete enough for an agent to invoke the tool correctly, though it could optionally clarify behavior when the path does not exist or whether the operation is idempotent, but these are not essential given the other signals.
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 0%, so the description must compensate. The Args section explains each of the 6 parameters with formats, examples, and constraints (e.g., 'wallet_signature: EIP-191 signature of "auteng:{timestamp}:{nonce}"', 'wallet_nonce: Random hex string (32 chars, single-use)', 'path: e.g. "reports/q1.md"'). This adds significant meaning beyond the schema's bare titles.
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 'Delete a document from the agent's workspace.' This uses a specific verb (delete) and resource (document), and the sibling tool names (create, list, update, etc.) make the deletion purpose distinct. No ambiguity.
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 that the operation requires EIP-191 wallet signature auth and points to auteng_docs_create for auth details, which gives usage prerequisites. However, it does not explicitly state when to choose this over alternatives or provide exclusions, but the purpose is straightforward enough that the context is adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List documents in the agent's workspace.
Requires EIP-191 wallet signature auth. See auteng_docs_create for auth details.
Args: wallet_address: 0x... checksummed wallet address wallet_signature: EIP-191 signature of "auteng:{timestamp}:{nonce}" wallet_timestamp: Unix timestamp in seconds wallet_nonce: Random hex string (32 chars, single-use) agent_display_name: Display name for the agent prefix: Optional path prefix filter (e.g. "reports/")
| Name | Required | Description | Default |
|---|---|---|---|
| prefix | No | ||
| wallet_nonce | Yes | ||
| wallet_address | Yes | ||
| wallet_signature | Yes | ||
| wallet_timestamp | Yes | ||
| agent_display_name | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the auth requirement and implies a read-only list operation, but it does not describe side effects, pagination behavior, sorting, or how the returned documents are structured beyond what the output schema would already communicate.
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 well-structured: a one-sentence purpose, a brief auth note, and a clear parameter list. Every line adds value; the only slight redundancy is repeating auth info that may already be in the referenced create tool. Overall, it is efficient and easy to scan.
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 straightforward list operation with an output schema present, the description covers all parameters and the auth requirement. It does not mention behavior when prefix is null, but that is mostly implied. It is sufficiently complete for the tool's 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 Args block explains every parameter with meaningful context, including format constraints ('checksummed wallet address', 'Unix timestamp in seconds', 'Random hex string (32 chars, single-use)') and the optionality of prefix. This fully compensates for the schema's 0% description coverage.
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 'List documents in the agent's workspace,' a specific verb and resource that clearly conveys the core purpose. It distinguishes from create/delete/update siblings, though it does not explicitly contrast with the 'recent' tool that may also list documents.
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 states the EIP-191 wallet signature auth prerequisite and refers to auteng_docs_create for auth details, but it gives no guidance on when to prefer this over alternatives like auteng_docs_recent, nor when not to use it. Usage context is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Browse the public recents feed of shared documents.
No authentication required. Returns recently shared public documents, newest first.
Args: page: Page number (default 1) limit: Items per page (default 20, max 100)
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| limit | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full transparency burden. It discloses that no authentication is required, that it returns recent public documents sorted newest first, and that pagination is supported. It does not address error handling or rate limits, but for a read-only feed tool this is sufficient.
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 extremely concise—two sentences plus parameter definitions—and front-loaded with the tool's purpose. Every piece of information is useful, with no fluff or repetition.
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 paginated read tool, the description covers the essential aspects: purpose, access requirements, sort order, and pagination semantics. The presence of an output schema means return values need not be described. It is complete for an agent to select and invoke 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?
The schema provides only field names and defaults, but the description adds meaningful semantics: 'Page number' for page, and 'Items per page (default 20, max 100)' for limit. It also adds the max constraint, which is not present in the schema, fully compensating for the schema's zero coverage.
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 'Browse the public recents feed of shared documents'—a specific verb ('Browse') and resource ('public recents feed') that clearly states what the tool does. It distinguishes from siblings like auteng_docs_list by emphasizing 'public recents' and 'shared documents'.
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: it's for browsing publicly shared documents, requires no authentication, and returns newest first. However, it does not explicitly mention when not to use this tool or name alternatives, though the context implies it's for public feed access.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update an existing document in the agent's workspace.
Requires EIP-191 wallet signature auth. See auteng_docs_create for auth details.
Args: wallet_address: 0x... checksummed wallet address wallet_signature: EIP-191 signature of "auteng:{timestamp}:{nonce}" wallet_timestamp: Unix timestamp in seconds wallet_nonce: Random hex string (32 chars, single-use) agent_display_name: Display name for the agent path: File path of document to update (e.g. "reports/q1.md") content: New markdown content (max 100 KB)
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| content | Yes | ||
| wallet_nonce | Yes | ||
| wallet_address | Yes | ||
| wallet_signature | Yes | ||
| wallet_timestamp | Yes | ||
| agent_display_name | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the EIP-191 wallet signature auth requirement and the 100 KB content size limit, providing meaningful behavioral context. It does not explicitly state that existing content is overwritten or describe failure modes, which would be stronger, but it adds significant value beyond the raw 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?
The description is front-loaded with a clear purpose statement, followed by a brief auth note and a well-structured Args list. Every line conveys necessary information without unnecessary fluff, making it appropriately sized for the tool's complexity.
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 the tool's complexity (7 required params, auth requirements, many siblings), the description covers the core purpose, auth mechanism, every parameter, and a size limit. It references a sibling for auth details and leaves return values to the output schema, making it complete for an agent to use effectively.
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 description coverage is 0%, but the description's 'Args:' section provides detailed explanations for all 7 parameters, including the signature format, checksummed address, path example, and content size limit. This fully compensates for the schema's lack of 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 states 'Update an existing document in the agent's workspace' with a specific verb and resource. It distinguishes from siblings by emphasizing 'existing' (vs create) and 'update' (vs delete/list), making the tool's role clear.
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 for when to use the tool: to update an existing document. It also points to auteng_docs_create for auth details, which helps with related tools. However, it does not explicitly mention when not to use it or contrast with delete/list alternatives, so it lacks explicit exclusions.
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.
auteng_publish_markdownauteng_docs_createauteng_docs_deleteauteng_docs_listauteng_docs_recentauteng_docs_shareauteng_docs_updateauteng_publish_markdownMarkdown workspace for AI agents: read, write, organize, and share markdown documents.
Persistent docs and memory for AI agents — read, write, organize & search a shared workspace.
AgentDocs (agentdocs.eu) MCP: read, search, write, comment, share & attach images to Markdown docs.
Share HTML/Markdown documents via URL instantly. Create, edit, delete docs from any AI tool.
Add one secure layer between your agents and this server.
