discover_categoriesFor a chosen chain, list its dynamic categories and compact category summaries. Call this after discover_networks and before search when you want deterministic retrieval.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | Yes | Canonical chain key from discover_networks, for example 'filecoin' | |
| analytics | No | Optional analytics context. It is ignored by tool execution and recorded only for usage analytics. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / analyticsAdded value: +{
+ "description": "Optional analytics context. It is ignored by tool execution and recorded only for usage analytics.",
+ "properties": {
+ "conversation_id": {
+ "description": "Optional conversation identifier.",
+ "type": "string"
+ },
+ "interaction_id": {
+ "description": "Optional interaction/message identifier.",
+ "type": "string"
+ },
+ "source": {
+ "description": "Optional analytics source identifier.",
+ "type": "string"
+ },
+ "user_query": {
+ "description": "Original user query or prompt that led to this tool call, if available.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. The word 'list' suggests a read-only operation, and 'deterministic retrieval' hints at stable output. However, it does not mention potential side effects, authorization requirements, error cases, or pagination, leaving some behavioral gaps. The phrase 'dynamic categories' adds context but does not fully clarify behavior.
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, immediately naming the action and resource, followed by a clear usage directive. Every word earns its place; there is no redundancy or 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?
The description gives enough context for a simple list operation: it indicates the input (chain), the output type (dynamic categories and compact summaries), and its place in the workflow. However, the lack of an output schema and any detail on return structure or limits means the agent must infer the exact shape of the 'compact category summaries.' The positioning and brevity keep it on the higher end.
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?
The schema already covers both parameters 100%, so the baseline is 3. The description adds value by specifying that 'chain' should come from discover_networks ('after discover_networks') and frames the output, which helps the agent understand the parameter's origin and purpose. It does not add new details about the analytics parameter, but the schema description already suffices.
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 verb 'list' and the resource ('dynamic categories and compact category summaries') for a chosen chain, which is specific. It also differentiates itself from siblings by positioning it after discover_networks and before search, making its role in the workflow distinct.
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?
Explicitly says 'Call this after discover_networks and before search when you want deterministic retrieval,' providing a clear sequencing instruction and a criterion for when to use it. This gives strong guidance relative to sibling tools and implies alternatives (discover_networks for networks, search for searching).
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 'execute' tool is a catch-all for registry actions, connection management, and runtime actions, creating ambiguity about when to use it versus the more specific discover_* and search tools. The other tools are distinct, but the overlap with execute's broad scope causes confusion.
Tool names mix bare verbs ('execute', 'search') with verb-noun patterns ('discover_categories', 'discover_networks'), plus one compound 'bind_credentials_bag'. This inconsistent style violates the predictable convention expected in a well-coherent tool set.
Five tools is within the ideal range for a focused MCP server. The count feels reasonable, though the broad scope of 'execute' suggests it may be absorbing many operations that could be split into more distinct tools.
The server covers discovery, search, and credential binding, but the generic 'execute' tool is the only gateway to mutations and connection management. This makes the surface technically complete but poorly structured, as significant functionality is hidden inside a single opaque entrypoint.