list_subscriptionsList the caller's active subscriptions. Returns id, type, params, created_at, last_fired_at, fire_count for each. Use this to review what you're monitoring before adding more or to find an id to cancel.
| Name | Required | Description | Default |
|---|---|---|---|
| include_inactive | No | Include cancelled subscriptions in the response (default false). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds context by listing specific return fields and usage scenarios, no contradictions.
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 with no wasted words: first states purpose and return fields, second gives usage guidance. Front-loaded and efficient.
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 1 optional parameter and no output schema, description adequately covers return fields and usage context. Could optionally mention parameter behavior, but not required.
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 has 1 optional parameter (include_inactive) with description, and schema coverage is 100%. Description does not mention the parameter, so 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?
Description clearly states the tool lists active subscriptions and enumerates return fields (id, type, params, etc.), distinguishing it from siblings like subscribe and unsubscribe.
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?
Explicitly states when to use it: 'review what you're monitoring before adding more or to find an id to cancel.' Does not explicitly mention alternatives, but sibling context implies separate tools for other actions.
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.
The server contains three ask_pipeworx variants, with ask_pipeworx_beta explicitly documented as 'currently matches ask_pipeworx exactly' — two functionally identical tools right now — and ask_pipeworx_grounded differing only in extraction mode. Five polymarket_* tools also occupy overlapping territory (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread), and meta-tools like discover_tools, suggest_questions, and pipeworx_trending blur together. Only the four URLhaus lookup tools are cleanly distinct.
There is good internal consistency within subgroups (lookup_host/payload/url, ask_pipeworx*, polymarket_*, remember/recall/forget), but across the full set conventions are mixed: verb-driven names (get_recent, list_subscriptions, validate_claim, generate_llms_txt) sit alongside plain noun names (entity_profile, bet_research, deep_research, recent_changes). The pattern is readable but lacks a single unifying scheme.
At 35 tools this is excessive for any single scope, but the deeper problem is that the server is named Urlhaus while roughly 30 of its 35 tools are unrelated Pipeworx/Polymarket infrastructure. The actual malware-mapping surface is only 4 tools; the rest is bolted-on and inflates the count well past the 25+ threshold for a heavy set.
For the server's intended URLhaus domain, the surface is read-only lookups (recent, host, payload, url) with no submission, payload-download, or tag-management operations, leaving obvious lifecycle gaps. Meanwhile the Pipeworx portion is all meta-framing around a single ask_pipeworx router, so neither domain is deeply or fully covered — the set is wide but shallow across many unrelated areas.