Save a query as a feed (needs a key). Sources, kinds and tags narrow; q is a text match; upcoming keeps only future-dated items.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Text match | |
| name | Yes | Feed name | |
| tags | No | Tags, any match | |
| kinds | No | Item kinds | |
| public | No | Default true | |
| sources | No | Source slugs | |
| upcoming | No | ||
| enrichers | No | Enrichers to show; omit for the collection defaults | |
| collection | Yes | Collection slug | |
| description | No | Optional |
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?
No annotations are present, so the description must carry the behavioral burden. It does disclose that a key is required and that 'upcoming' affects date filtering, which adds some context. However, it lacks consequences of creating duplicate feeds, side effects on existing feeds, or what the response will look like—important for a write operation with no annotation support.
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 compact: two sentences, with the main purpose front-loaded and parameter nuances in a single follow-up sentence. Every phrase earns its place, though the parenthetical 'needs a key' is slightly cryptic and the comma-separated list could be clearer to parse.
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 tool with 10 parameters, no output schema, and no annotations, the description is adequate but not complete. It explains only a few parameters and mentions a key requirement without specifying what key or where to get it. The high schema coverage fills most gaps, but creation behavior and response format remain undocumented.
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 description coverage is high at 90%, so the baseline is 3. The description adds value by clarifying that 'Sources, kinds and tags narrow' and that 'upcoming' means only future-dated items are kept—both go beyond the schema's sparse descriptions. It does not redundantly repeat every parameter, only the ones needing explanation.
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 specific verb and resource, 'Save a query as a feed', which clearly identifies the operation. It also notes the auth requirement ('needs a key'). It does not explicitly distinguish itself from sibling tools, but the sibling list contains no other create/save operation, so ambiguity is low.
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 implies the intended use case—when you want to persist a query as a feed—but provides no explicit when-or-when-not guidance or mentions of alternatives like list_feeds or feed_items. It is sufficient for an obvious create operation but does not actively route the agent away from related tools.
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.