Skip to main content
Glama

mark_as_unread

Mark articles as unread in FreshRSS to revisit them later. Specify article IDs to reset their read status for future review.

Instructions

Mark one or more articles as unread

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
articleIdsYesArticle IDs to mark

Implementation Reference

  • The handler function that executes the mark_as_unread tool logic using the client service.
    wrapTool('mark_as_unread', async (args: z.infer<typeof markArticlesSchema>) => {
      await client.articles.markAsUnread(args.articleIds);
      return textResult(`Marked ${args.articleIds.length.toString()} article(s) as unread.`);
    })
  • The service method that performs the actual API call to mark articles as unread.
    async markAsUnread(articleIds: string[]): Promise<void> {
      await this.http.post('/reader/api/0/edit-tag', {
        i: articleIds,
        r: 'user/-/state/com.google/read',
      });
  • Tool registration for 'mark_as_unread' in the server.
    server.registerTool(
      'mark_as_unread',
      {
        description: 'Mark one or more articles as unread',
        inputSchema: markArticlesSchema,
      },
      wrapTool('mark_as_unread', async (args: z.infer<typeof markArticlesSchema>) => {
        await client.articles.markAsUnread(args.articleIds);
        return textResult(`Marked ${args.articleIds.length.toString()} article(s) as unread.`);
      })
    );
  • Input validation schema for marking articles.
    export const markArticlesSchema = z
      .object({
        articleIds: z.array(z.string()).min(1).describe('Article IDs to mark'),
      })
      .strict();
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. While 'mark' implies a state mutation, the description does not clarify whether this is a destructive operation, if it is idempotent, or what happens when article IDs do not exist. It fails to disclose write-specific behaviors like authentication requirements or rate limiting.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of a single, efficient sentence that leads with the action verb and specifies scope without filler words. Every word serves to clarify the operation's intent and cardinality. No restructuring or compression is needed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter state-change operation with complete schema documentation, the description covers the essential functional contract. However, given the absence of annotations and output schema, the lack of behavioral context (side effects, error conditions) and differentiation from similar tools leaves minor gaps in contextual completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage with 'Article IDs to mark', establishing a baseline understanding. The description adds the constraint 'one or more' which reinforces the schema's `minItems: 1` requirement, but does not elaborate on ID format, source, or validation rules. Since the schema fully documents the parameter, additional semantic detail is minimal.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Mark one or more articles as unread' provides a specific verb (mark), resource (articles), and target state (unread). It implicitly distinguishes from the sibling tool `mark_all_as_read` by specifying 'one or more' rather than 'all'. However, it does not explicitly contrast with `mark_as_read` to clarify when to mark as unread versus read.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus its siblings like `mark_as_read` or `mark_all_as_read`. It does not specify prerequisites such as needing valid article IDs from `list_articles` or whether this operation is reversible. Without explicit when-to-use context, the agent must infer from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/alysson-souza/freshrss-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server