get_storyFetch a single story and all its comments by ID (e.g., "abc123"). Returns title, URL, text, score, and nested comment threads.
| Name | Required | Description | Default |
|---|---|---|---|
| short_id | Yes | The short alphanumeric story ID from the Lobsters URL (e.g. "abcdef") |
| Name | Required | Description | Default |
|---|---|---|---|
| story | Yes | The story details | |
| comments | Yes | List of comments on the story |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "comments": {
+ "description": "List of comments on the story",
+ "items": {
+ "properties": {
+ "author": {
+ "description": "Username of comment author",
+ "type": "string"
+ },
+ "body": {
+ "description": "Comment text (plain text)",
+ "type": "string"
+ },
+ "created_at": {
+ "description": "ISO timestamp of comment creation",
+ "type": "string"
+ },
+ "indent_level": {
+ "description": "Nesting level in comment thread",
+ "type": "number"
+ },
+ "is_deleted": {
+ "description": "Whether comment is deleted",
+ "type": "boolean"
+ },
+ "is_moderated": {
+ "description": "Whether comment is moderated",
+ "type": "boolean"
+ },
+ "score": {
+ "description": "Total comment score",
+ "type": "number"
+ },
+ "short_id": {
+ "description": "Unique short ID for the comment",
+ "type": "string"
+ },
+ "url": {
+ "description": "Direct URL to the comment",
+ "type": "string"
+ }
+ },
+ "required": [
+ "short_id",
+ "url",
+ "created_at",
+ "score",
+ "indent_level",
+ "author",
+ "body",
+ "is_deleted",
+ "is_moderated"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "story": {
+ "description": "The story details",
+ "properties": {
+ "comment_count": {
+ "description": "Number of comments",
+ "type": "number"
+ },
+ "comments_url": {
+ "description": "URL to view comments on Lobsters",
+ "type": "string"
+ },
+ "created_at": {
+ "description": "ISO timestamp of story creation",
+ "type": "string"
+ },
+ "description": {
+ "description": "Plain text description or null",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "downvotes": {
+ "description": "Number of downvotes",
+ "type": "number"
+ },
+ "score": {
+ "description": "Total score (upvotes - downvotes)",
+ "type": "number"
+ },
+ "short_id": {
+ "description": "Unique short ID for the story",
+ "type": "string"
+ },
+ "submitter": {
+ "description": "Username of story submitter",
+ "type": "string"
+ },
+ "tags": {
+ "description": "Tags associated with the story",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "title": {
+ "description": "Story title",
+ "type": "string"
+ },
+ "upvotes": {
+ "description": "Number of upvotes",
+ "type": "number"
+ },
+ "url": {
+ "description": "Story URL",
+ "type": "string"
+ }
+ },
+ "required": [
+ "short_id",
+ "url",
+ "comments_url",
+ "title",
+ "score",
+ "upvotes",
+ "downvotes",
+ "comment_count",
+ "created_at",
+ "submitter",
+ "tags",
+ "description"
+ ],
+ "type": "object"
+ }
+ },
+ "required": [
+ "story",
+ "comments"
+ ],
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "short_id": "abcdef"
+ },
+ {
+ "short_id": "xyz789"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and non-destructive hint. Description adds return details (nested comments, fields) but no additional behavioral context beyond annotations.
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?
Single sentence, front-loaded with key action and resource. No wasted words.
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?
Tool is simple (one param, output schema exists). Description covers purpose and return value sufficiently. No missing information for a straightforward fetch operation.
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% with a clear description. The description adds an example format but does not significantly enhance understanding beyond the schema. Baseline score of 3.
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?
Description clearly states verb ('Fetch'), resource ('a single story and all its comments'), and output fields. It distinguishes from sibling list tools (e.g., get_hottest) by specifying 'single story'.
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 (need a story ID), but no explicit when-to-use, when-not-to-use, or alternatives among siblings are mentioned. Adequate but not explicit guidance.
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.
Many tools have overlapping purposes, e.g., three tools for querying Pipeworx data (ask_pipeworx, ask_pipeworx_grounded, deep_research), and six tools for Polymarket prediction markets. The boundaries between them are unclear, causing potential for misselection.
Tool names are all snake_case but follow inconsistent patterns: some use verb_noun (get_hottest, get_newest), some are single verbs (remember, forget), and others are noun_noun (bet_research, polymarket_arbitrage). While readable, the lack of a consistent pattern adds confusion.
With 34 tools, the server is overloaded, especially given its name 'Lobsters' suggests a focus on that site, yet only 4 tools are Lobsters-related. The majority belong to Pipeworx, Polymarket, and generic utilities, making the scope extremely broad and unfocused.
For the implied domain of Lobsters, the tool set is incomplete (missing create/update/delete). For the broader domains (Pipeworx, Polymarket), the set is extensive but doesn't align with the server's name. The lack of a coherent domain leaves obvious gaps relative to any single purpose.