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 already declare readOnly, idempotent, non-destructive. Description adds return field details but no further 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?
Two efficient sentences: first states action and return fields, second explains when to use. No fluff.
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 simple operation with one optional param and no output schema, description is complete: lists return fields, explains usage purpose, and ties to sibling subscribe/unsubscribe.
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 clear description for include_inactive. No need for additional parameter explanation in description; baseline 3 applies.
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 'List the caller's active subscriptions' and lists return fields (id, type, params, etc.). Distinguishes from sibling subscribe/unsubscribe as a listing tool.
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 says 'Use this to review what you're monitoring before adding more or to find an id to cancel.' Provides clear context for when to use, though could mention when not to use.
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 set contains multiple overlapping families: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all answer natural-language data questions, while five polymarket tools and ai_visibility_check/scan_competitor_ai_presence further blur boundaries. The lengthy descriptions help, but an agent will still face genuinely ambiguous selection decisions across these clusters.
Tool names mix verb-first patterns (find_stations, validate_claim), domain-first names (polymarket_edges, entity_profile), and brand-prefixed meta tools (pipeworx_trending, pipeworx_feedback). Snake_case is consistent, but there is no predictable verb_noun convention across the set, making the overall naming scheme feel more like a platform catalog than a coherent API.
At 34 tools, this is too many for a well-scoped server, and most of the surface (prediction markets, AI visibility, npm scanning, llms.txt generation) is unrelated to the server's stated Meteostat identity. The count is driven by broad meta wrappers and overlapping data-access aggregates rather than a focused domain model.
For a server named Meteostat, the weather surface is notably incomplete: find_stations plus get_daily_history and get_monthly_normals covers stations, daily records, and normals, but there is no current-conditions, forecast, or hourly-history tool even though hourly availability is mentioned in station inventories. The rest of the set is a broad data-research layer, but it does not form a complete lifecycle for any single resource.