Deterministic manifest→tag mapping. Given files + languages + git_origin, returns up to 8 skill slugs and up to 5 personas, each with the reason it fired. No LLM classification.
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | ||
| languages | No | ||
| git_origin | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses determinism, maximum output counts (8 skill slugs, 5 personas), and that each result includes a 'reason it fired'. It also states 'No LLM classification', which is a meaningful behavioral exclusion. It does not mention side effects or error conditions, but the mapping nature implies read-only 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 two sentences long, with no unnecessary words. The first sentence provides a high-level label, and the second elaborates with concrete details. Every clause adds value, making it highly concise and well-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?
The description explains the core function and output shape but lacks an output schema, leaving the exact return format ambiguous. It does not cover edge cases such as empty results, optional parameters, or potential errors. Given the moderate complexity (3 params) and lack of annotations/output schema, this is only partially complete.
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%, so the description must compensate. It names all three parameters ('files', 'languages', 'git_origin') but provides no additional meaning beyond their existence. There is no format, example, or constraint provided for any parameter, leaving the agent to infer what values are expected.
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 a specific verb ('returns') and resource ('skill slugs and personas'), with explicit inputs ('files + languages + git_origin'). It distinguishes itself from siblings by emphasizing 'No LLM classification', making its non-LLM, rule-based nature clear.
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 usage context through 'Deterministic' and 'No LLM classification', suggesting it is for when a rule-based suggestion is preferred. However, it does not explicitly state when to use this tool versus alternatives, nor does it name any sibling tool for comparison.
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 have clearly distinct purposes with detailed descriptions, but a few boundaries are fuzzy: leave_message vs ask_human vs leave_comment, and list_content vs list_collection could confuse an agent at first glance. Overall, the descriptions are thorough enough to disambiguate.
The naming convention is predominantly snake_case with verb_noun structure (list_content, read_blob, upsert_skill). Minor deviations exist such as the mysloodsiewnia_* prefix and British spelling in synthesise_persona_patterns, but the pattern is highly recognizable and readable.
At 41 tools, the surface area is very large for a single MCP server and exceeds the 'heavy' threshold. While each tool serves a distinct purpose, the sheer number makes the server feel bloated and harder to navigate; many tools could be grouped or pruned without losing core functionality.
The server covers a broad domain: content read/list, personas, skills management, vault CRUD (except update/delete intentionally), provenance, licensing, memory, and async question/narada workflows. Minor gaps exist like no tool to cancel a narada job or update a memory, but these are workable and the core workflows are well supported.