MCP subregistry (GET /v0.1/servers). Only live kind=mcp.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Servers per page. | |
| cursor | No | Opaque cursor of the next page, from `metadata.next_cursor`. | |
| search | No | Free text over the server's name and description. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / cursor / descriptionAdded value: +"Opaque cursor of the next page, from `metadata.next_cursor`."Input schema / properties / limit / defaultAdded value: +30Input schema / properties / limit / descriptionAdded value: +"Servers per page."Input schema / properties / search / descriptionAdded value: +"Free text over the server's name and description."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the endpoint and filter but does not disclose behavior like pagination, rate limits, auth requirements, or what happens with no results. The return format is also not mentioned, leaving the agent to infer from the endpoint.
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, compact sentence with no wasted words. It includes the endpoint and a key filter. It could be slightly more informative, but it is 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?
For a listing tool with pagination parameters (limit, cursor) and no output schema, the description is thin. It does not explain the return structure or how the cursor pagination works in practice. The schema covers parameter syntax, but the description lacks context on expected usage patterns, which an agent would need for reliable invocation.
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 100%, so the parameters are already documented. The description adds no extra meaning about the parameters; it only implies a filter via 'kind=mcp' but does not elaborate on how parameters like search interact with that filter. Baseline 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?
The description clearly states the resource (MCP subregistry) and the specific endpoint (GET /v0.1/servers), and adds a distinct filter ('Only live kind=mcp'). This is specific enough to distinguish from sibling list tools like list_listings or list_comments.
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?
No guidance is provided on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or compare against sibling tools. The context is implied by the name and endpoint but not explicit.
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 are clearly separated by resource/action (listings, comments, servers, billing, health). The main ambiguity is among get_listing, get_listing_readme, and go_listing, which all involve retrieving or routing to a listing but return different things.
The set mostly follows a verb_noun snake_case convention (create_listing, get_listing_readme, list_comments, like_listing). A few bare endpoint-style names (billing, contact, health, api_index) break the pattern but are still recognizable.
Thirteen tools is a reasonable size and each area—registry, comments, billing, health—has at least one tool. The count is not bloated, though the mixed domains make it feel slightly less focused than a single-purposed server.
The listing registry covers create, get, list, like, visit, and readme retrieval, but lacks obvious update/delete operations and any way to create comments. The billing/contact side is also thin, exposing prices and one paid action rather than a fuller payment flow.