siteFetch instance-level metadata for a Lemmy instance (default lemmy.world), including site name, description, version, admin info, and federated instances list.
| Name | Required | Description | Default |
|---|---|---|---|
| instance | No |
| Name | Required | Description | Default |
|---|---|---|---|
| admins | No | List of instance admins | |
| site_view | No | Site metadata and statistics | |
| all_communities | No | All communities on instance |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "instance": "lemmy.world"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "description": "Response from Lemmy API /site endpoint",
+ "properties": {
+ "admins": {
+ "description": "List of instance admins",
+ "items": {
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "all_communities": {
+ "description": "All communities on instance",
+ "items": {
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "site_view": {
+ "description": "Site metadata and statistics",
+ "type": "object"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds behavioral context by enumerating specific metadata fields returned. It does not disclose potential network latency or rate limits, but for a simple read operation this is acceptable.
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 concise sentence that front-loads the action and resource, enumerates the key returned data, and states the default. Every word contributes to understanding, with no filler or redundancy.
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?
Given the tool has an output schema (not detailed here), the description does not need to explain return values. The description covers the tool's purpose, default behavior, and content scope adequately for a simple read-only metadata fetcher. Minor gap: it does not explicitly explain how the 'instance' parameter is formatted, but the example and default mitigate this.
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?
Input schema has one parameter 'instance' with no description, so schema description coverage is 0%. The description mentions 'default lemmy.world', which implies the parameter is used to specify a different instance, but it does not explicitly state that 'instance' is the domain name of the Lemmy instance. This leaves some ambiguity, though the example in the schema partially compensates.
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 ('Fetch') and a clear resource ('instance-level metadata for a Lemmy instance'), and lists the key contents (site name, description, version, admin info, federated instances list). It differentiates itself from sibling tools that target communities, posts, or search by focusing on instance-level metadata.
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 when to use the tool: when you need instance-level metadata. It also provides a default value (lemmy.world), giving context for the common use case. However, it does not explicitly name alternatives or state when not to use it, so it falls short of full exclusion criteria.
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.
Many tools have overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all answer factual questions, while bet_research, polymarket_edges, polymarket_arbitrage, and polymarket_fill_risk all analyze prediction markets. The Lemmy tools are distinct from the Pipeworx tools, but within each cluster an agent could easily select the wrong tool despite lengthy descriptions.
Naming conventions are mixed: single nouns (post, community, site), verb_noun patterns (list_subscriptions, resolve_entity, generate_llms_txt), and ad-hoc names (ask_pipeworx, forget, recall). There is no consistent verb_noun or noun-only pattern across the set, making it hard to predict tool names.
38 tools is excessive for a server named 'Lemmy' where only 7 tools (comments, communities, community, post, posts, search, site) actually relate to Lemmy. The vast majority of tools belong to an unrelated Pipeworx data platform, creating a severe scope mismatch and making the server feel bloated and unfocused.
For the Lemmy domain, the tools cover read-only browsing (list posts, view post, list communities, fetch community, comments, search, site metadata) but completely lack write operations like posting, commenting, voting, or moderation. The Pipeworx tools are extensive but do not compensate for the primary domain's gaps since the server is ostensibly about Lemmy.