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 read-only, idempotent, non-destructive. Description adds return fields and default behavior (active only). Does not mention pagination or limits, but adequate for simplicity.
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 plus a brief list of return fields. Every sentence is purposeful: purpose, usage, output. Front-loaded and concise.
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?
For a simple listing tool with one optional parameter and no output schema, the description covers purpose, usage, return fields, and parameter behavior completely.
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 covers 100% of parameters. Description reinforces the default (active subscriptions) implied by the optional include_inactive flag, adding context 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?
Description clearly states 'List the caller's active subscriptions' and enumerates return fields. Distinguishes from sibling tools 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: 'to review what you're monitoring before adding more or to find an id to cancel.' Implies alternatives (subscribe, unsubscribe).
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 separated jobs, but the set is crowded with overlapping research/query entry points: ask_pipeworx and ask_pipeworx_beta are described as currently identical, and the Polymarket/research cluster has fuzzy boundaries. Detailed descriptions help, but an agent can still easily mis-select among these tools.
Names are consistently snake_case and readable, but they mix verb-led commands (get_dataset, list_editions, validate_claim) with noun-led descriptive names (entity_profile, polymarket_edges, recent_changes) and a version-suffixed duplicate (ask_pipeworx_beta). The ONS tools also lack a shared ons_ prefix aside from ons_timeseries, so the naming is more a collection of conventions than one predictable pattern.
37 tools is well past the heavy range for a server whose name suggests a focused UK ONS statistics surface; only about six tools actually serve ONS data, while the rest span memory, subscriptions, prediction markets, npm scanning, AI visibility, and general Pipeworx plumbing. The count is not an extreme 50+ sprawl, but it is too many for a coherent scope.
The core ONS read workflow is well covered: catalog discovery through list_datasets, dataset/edition/version metadata, filtered get_observations, and classic time series via ons_timeseries. Minor gaps exist, such as no dedicated dataset search and some peripheral one-off features like scan_dependency or generate_llms_txt, but agents can work around them.