Registers an MCP server, skill or plugin (human session free; agent without session = 402 $0.10).
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | MCP endpoint, SKILL.md URL or the plugin's repository. | |
| body | No | Long description, optional. | |
| kind | Yes | What is being registered. | |
| name | No | Display name; without it, taken from the source. | |
| tagline | No | One line saying what it is for. | |
| category | No | Category so the listing shows up under the right filter. | |
| session_token | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / body / descriptionAdded value: +"Long description, optional."Input schema / properties / category / descriptionAdded value: +"Category so the listing shows up under the right filter."Input schema / properties / kind / descriptionAdded value: +"What is being registered."Input schema / properties / kind / enumAdded value: +[
+ "mcp",
+ "skill",
+ "plugin"
+]Input schema / properties / name / descriptionAdded value: +"Display name; without it, taken from the source."Input schema / properties / tagline / descriptionAdded value: +"One line saying what it is for."Input schema / properties / url / descriptionAdded value: +"MCP endpoint, SKILL.md URL or the plugin's repository."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It does reveal a non-obvious session/pricing behavior ('agent without session = 402 $0.10'), but it does not state side effects of registration, whether listings can be overwritten, or what the response looks like.
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 core purpose is front-loaded in a single sentence, and the parenthetical is compact. It is slightly dense, especially the '402 $0.10' pricing note, but overall it earns its place without unnecessary filler.
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 7-parameter create operation with no output schema and no annotations, one sentence leaves gaps: no statement of what a successful registration returns, whether updates are possible, or requirements like session_token. The schema covers parameter semantics, but behavioral context is thin.
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 high at 86%, so the schema already documents most parameters. The description adds only the mapping from resource types to 'kind' and an implicit reference to session cost, with no new detail on body, name, tagline, or category.
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 uses a specific verb ('Registers') and names the exact resource types (MCP server, skill, or plugin), which maps directly to the 'kind' enum and clearly distinguishes it from siblings like get_listing or list_listings.
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?
There is no guidance on when to use this tool versus alternatives such as get_listing or list_listings. The only conditional information is the session/pricing parenthetical, which addresses cost rather than tool selection.
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 target distinct resources or actions, and descriptions are clear enough to avoid major confusion. The main overlap is between list_listings and list_mcp_servers as registry views, though their scope differs.
The set mixes verb_noun names like create_listing and list_comments with noun-style names like api_index, billing, contact, and health. This is readable but not a consistent naming convention across the whole server.
Twelve tools is a reasonable, well-scoped count for a registry-and-commerce server. Each tool has a distinct role, with no obvious bloat or redundancy.
Discovery, creation, liking, and commenting are covered, but there are no update or delete operations for listings, nor any comment management beyond listing comments. These are notable lifecycle gaps for a registry-style tool.