list_data_classesCanonical list of HIBP "data class" tags (e.g., "Email addresses", "Passwords", "Geographic locations"). Useful for filtering breaches.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | Number of data classes | |
| data_classes | Yes | Canonical HIBP data class tags |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {}
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "count": {
+ "description": "Number of data classes",
+ "type": "number"
+ },
+ "data_classes": {
+ "description": "Canonical HIBP data class tags",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "count",
+ "data_classes"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide comprehensive behavioral hints (readOnlyHint, openWorldHint, idempotentHint, destructiveHint). The description adds 'Canonical list', which might imply completeness, slightly conflicting with openWorldHint (suggesting non-exhaustive). Apart from that, the description does not add significant 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?
The description is two sentences long and immediately front-loads the essential information. Every word serves a purpose; no filler or redundancy.
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 has no parameters, comprehensive annotations, and an output schema, the description adds enough context about the purpose and use case. It lacks explanation of the output format, but the output schema can cover that. A minor gap is the possible contradiction with openWorldHint, but overall it is reasonably complete.
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 tool has zero parameters and schema coverage is 100%, so no parameter documentation is needed. The description adds value by explaining what data classes are with examples, which aids understanding beyond the schema.
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's function: 'Canonical list of HIBP data class tags'. It uses a specific verb ('list') and resource ('data classes'), and provides examples like 'Email addresses', 'Passwords'. Among siblings, no other tool appears to list data classes exclusively, so it distinguishes well.
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 mentions 'Useful for filtering breaches', which gives a usage context. However, it does not explicitly contrast with siblings like 'get_breach' or 'list_breaches', nor does it state when not to use it. The guidance is present but minimal.
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.
Most tools have clearly distinct purposes, and the long, detailed descriptions make it easy for an agent to pick the right one. However, there is some functional overlap between research-oriented tools (e.g., ask_pipeworx vs deep_research vs bet_research) and between visibility-checking tools (ai_visibility_check vs scan_competitor_ai_presence), which could potentially confuse an agent without careful reading.
Tool names are uniformly lowercase with underscores, and related tools share consistent prefixes (e.g., polymarket_*, ask_pipeworx, check_*). While most follow a verb_noun pattern, some are noun-first (entity_profile, polymarket_arbitrage) or compound (scan_competitor_ai_presence), creating minor inconsistency, but overall the naming is readable and not chaotic.
With 37 tools, the count is on the higher end but appropriate for a broad data/research platform that covers HIBP breaches, multiple data-pull/research modes, Polymarket analytics, memory, subscriptions, and meta-tools. The number is justified by the diversity of capabilities, though it exceeds the typical 3-15 range for a narrowly-scoped server.
The tool set appears thorough for its intended scope: HIBP breach lookup is fully covered (check_account, check_password, get_breach, list_breaches, list_data_classes), research and entity resolution are extensive (entity_profile, compare_entities, deep_research, validate_claim, etc.), Polymarket has dedicated arbitrage/edge/fill-risk tools, and memory/subscription/meta capabilities are present. No obvious gaps for the stated functionality.