Projects built and shipped by Laurent Knauss (agentic AI products and full-stack web apps), with domain, live status, one-line positioning and tech stack. Use it to assess his delivery track record — get_project returns the full description.
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | Filter by status: live (deployed in production) or oss (open source, not deployed). | |
| category | No | Filter by project family: ai (agentic AI) or web. |
Changes observed during successful MCP inspections.
Input schema / properties / status / descriptionPrevious value: -"Filter by status: live (in production) or soon."New value: +"Filter by status: live (deployed in production) or oss (open source, not deployed)."Input schema / properties / status / enumPrevious value: -[
- "live",
- "soon"
-]New value: +[
+ "live",
+ "oss"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It explains what the returned list contains and that it is a high-level overview, but it does not state that the call is read-only, that filters are optional, or describe response ordering/pagination. The absence of side effects is implied by 'list' rather than stated.
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?
Two compact sentences front-load the result content, state the purpose, and route to the sibling tool. Every clause earns its place.
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 filtered list tool with no output schema, it covers what results contain and directs the agent to get_project for deeper detail. It could be slightly more explicit about the effect of omitting both filters (returns all projects), but the schema already documents the available filters.
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 100% with well-documented enum params, so the baseline is 3. The description's references to 'live status' and 'agentic AI products and full-stack web apps' loosely map to status and category but add no syntax or semantics beyond the schema.
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 ('list') and resource ('projects'), names the owner (Laurent Knauss) and describes the returned fields: domain, live status, positioning, tech stack. It also distinguishes itself from get_project by noting that tool returns the full description.
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?
Gives clear when-to-use guidance: 'Use it to assess his delivery track record' and points to get_project for the full description. It does not explicitly list exclusions or say when get_project should be preferred over this tool, but the alternative is named.
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.