MidOS Research Protocol MCP

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses critical behavioral detail that stack filters 'boost' rather than filter results. With no annotations provided, description carries full burden but omits safety status (read-only), rate limits, or output structure (though output schema exists).

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?

Efficient structure with purpose front-loaded, clear Args section, and zero redundant sentences. Technology specifics (LanceDB/Gemini) earn their place by distinguishing implementation approach.

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?

Given output schema exists, description appropriately focuses on input semantics and search behavior. Parameter documentation is complete. Minor gap: without annotations, should ideally declare read-only/safe status explicitly.

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?

Excellent compensation for 0% schema description coverage. Documents all 3 parameters with natural language meaning, data types (implied), defaults (top_k), format constraints (comma-separated), and behavioral effects (boosting).

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 specific mechanism (LanceDB vectors, Gemini embeddings) and distinguishes from siblings via 'More intelligent than keyword search.' Loses one point for not explicitly naming the searchable corpus (e.g., knowledge base, documents).

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?

Implies usage context by contrasting with keyword search, suggesting when semantic understanding is needed. However, lacks explicit 'Use this when...' guidance or named alternatives (e.g., search_knowledge).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.