Follow a feed as the key owner (needs a key). Channels: webpush, email, webhook.
| Name | Required | Description | Default |
|---|---|---|---|
| feed | Yes | Feed slug | |
| channels | No | Default webpush,email | |
| webhook_url | No | For the webhook channel | |
| webhook_secret | No | Shared secret the receiver verifies with |
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?
With no annotations, the description carries the behavioral disclosure burden. It usefully reveals that a key is required and that channels are restricted to webpush, email, and webhook. However, it does not state side effects, idempotency, what state gets changed, or what happens after following, so the disclosure is only partial.
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 a single front-loaded sentence: the action and actor come first, followed by a compact channel list. Every phrase carries information and there is no filler or repetition.
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?
Crucial operational context is present: the action, the key requirement, and the supported channels, with parameters fully documented in the schema. Still, there is no output schema and no explanation of what 'following' does, what a successful call returns, or how failures behave, so an agent may need external knowledge to invoke it confidently.
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%, so the baseline is 3. The description adds value by enumerating the accepted channel values (webpush, email, webhook), which the schema only partially conveys by listing a default. This helps an agent construct valid channel arguments.
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 opens with a concrete verb-resource pair ('Follow a feed') and names the necessary actor ('key owner'), which clearly identifies the operation. It does not explicitly differentiate from sibling tools, but none of the siblings are follow-like, so the purpose is unambiguous.
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 gives an explicit prerequisite ('needs a key') and lists valid channels, which implies when the tool can be used. It does not name alternatives or conditions for choosing another tool, so routing guidance is left mostly to inference.
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 tools are mostly distinct: list_* tools cover different metadata resources, and item queries are separated into recent_items, search_items, upcoming, and feed_items. Some overlap exists among the item-retrieval tools, but descriptions clarify their different filters and use cases.
Most tools follow a verb_noun pattern such as add_source, create_feed, list_* and search_items. A few exceptions like feed_items, stats, and upcoming break the pattern, but the overall naming is still predictable and readable.
Fifteen tools is well within the expected range and each tool maps to a distinct part of the domain: adapters, sources, collections, enrichers, feeds, items, and stats. The count feels appropriate for the breadth of NicheDB without obvious bloat.
The read and query surface is strong, covering items, feeds, sources, collections, and enrichers. However, lifecycle management is incomplete: sources and feeds can be created but not updated or deleted, and feeds can be followed but not unfollowed, which leaves notable admin workflow gaps.