Lists AI skills provided by installed QUIQQER packages. Use at the start of non-trivial QUIQQER tasks when package-specific instructions may apply. Match the returned descriptions to the task and load the relevant skills with quiqqer_skill_get before making changes.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No |
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 does clearly indicate a read-style list operation and notes that results are descriptions, and 'before making changes' implies non-mutating intent. However, it does not disclose return structure, filtering behavior, pagination, or any permission/side-effect caveats.
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 three short sentences with the purpose front-loaded. Every clause earns its place: purpose, usage context, and recommended next action. There is no filler or repetition.
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 one-optional-parameter list tool, the description provides solid what/when/next guidance and mentions 'returned descriptions,' which helps despite the lack of an output schema. However, the missing `category` semantics and lack of differentiation from `quiqqer_mcp_skill_list` leave noticeable 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?
Schema description coverage is 0%, and the tool description never mentions the `category` parameter. An agent cannot tell what values are valid, whether `category` filters or groups results, or how the default `null` behaves. The parameter name and type only weakly imply an optional filter.
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 first sentence uses a specific verb, 'Lists', and a specific resource, 'AI skills provided by installed QUIQQER packages', so an agent can tell what the tool does. It loses the top score because the sibling `quiqqer_mcp_skill_list` appears to cover the same action and the description does not differentiate between them.
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 explicitly states when to use the tool: 'at the start of non-trivial QUIQQER tasks when package-specific instructions may apply.' It also names the follow-up action and alternative tool, `quiqqer_skill_get`, and instructs the agent to load relevant skills before making changes.
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 two list tools and two get tools are functionally identical, differing only by prefix. An agent cannot reliably determine whether to call quiqqer_mcp_skill_get or quiqqer_skill_get, though list vs get is at least clear.
The set mixes quiqqer_mcp_skill_* and quiqqer_skill_* naming conventions for the same operations, and the server name 'IBAN Validation MCP' has no relation to QUIQQER or skill retrieval. No predictable naming pattern emerges.
Four tools is not an unreasonable number, but the surface is padded with two duplicate pairs that reduce the effective count to two. The count is acceptable only if the redundancies are treated as accidental.
Given the server name, users would expect IBAN validation operations, but the tools only retrieve QUIQQER skill metadata and instructions. There are no validation, format-checking, or account-related operations at all.
