Search directory listings by query/category/tag (unranked educational match). Educational only. Not financial advice. Not an FSP/CASP. DYOR. Listings and tools are not buy, sell, custody, or swap recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| tag | No | ||
| category | No |
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?
With no annotations provided, the description carries the burden of behavioral disclosure. It adds useful context by describing results as 'unranked educational match' and by warning that listings and tools are not recommendations. However, it does not mention operational traits like auth requirements, rate limits, or output behavior, though a search is implicitly non-destructive.
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 and the description is not overly long. However, the legal disclaimers are repeated and could be condensed; several clauses make the same 'not advice/recommendation' point. It is serviceable but not tightly structured.
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 simple search tool with no output schema, the description establishes the purpose, scope, result nature, and domain constraints. It does not specify return format, pagination, empty-result behavior, or parameter interactions, but these are partly inferable from the name and schema. Adequate with clear gaps.
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 description maps the parameters by saying 'query/category/tag', which clarifies that 'q' is a free-text query while 'category' and 'tag' echo their own names. With 0% schema description coverage, this is helpful but shallow: it does not explain how the parameters combine, whether they are filters or mutually exclusive, or what values are valid.
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?
States a specific verb, 'Search', a resource, 'directory listings', and the search dimensions 'query/category/tag'. This makes the main purpose clear, but it does not explicitly contrast with siblings like list_directory or search_content, so differentiation is left mostly to the resource name.
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 given for when to use this tool versus alternatives such as list_directory or search_content. The disclaimers ('Educational only', 'Not financial advice', etc.) impose domain constraints but do not help with tool selection or invocation context.
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.
list_directory and search_directory accept nearly identical filters (q, category, tag), so their boundaries blur. The get_/list_/search_ split is otherwise clear, and the meta endpoints (disclaimer, site_posture, llms_map) are distinct though thematically related.
All tool names consistently follow a verb_noun snake_case pattern using only get_, list_, and search_. There are no mixed conventions, vague verbs, or unpredictable naming.
Twelve tools is within a reasonable range for a read-only educational content server. However, the overlap between list_directory and search_directory suggests the surface could be slightly trimmed without losing core functionality.
The server covers directory browsing, educational content listing and searching, metrics, and site-positioning meta endpoints well. Missing per-item getters for guides and notes is a minor gap since lists include URLs and search covers those types; write operations are not expected for an educational-only server.