MidOS Research Protocol

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the search uses LanceDB vectors and Gemini embeddings, which adds some context, but doesn't cover critical aspects like authentication needs, rate limits, error handling, or what the output contains. For a search tool with zero annotation coverage, this leaves significant gaps in understanding its 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 well-structured and front-loaded with the core purpose, followed by a concise 'Args' section that efficiently explains each parameter. Every sentence earns its place, with no redundant information, making it easy to scan and understand quickly.

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 the tool's moderate complexity (3 parameters, no annotations), the description does a good job covering the basics: purpose, parameters, and differentiation from keyword search. Since there's an output schema, it doesn't need to explain return values. However, it could improve by addressing behavioral aspects like performance or limitations, given the lack of annotations.

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 provides clear semantics for all three parameters: 'query' as a natural language query with an example, 'top_k' as the number of results with a default, and 'stack' as an optional filter with an example and effect ('boosted'). This adds substantial value beyond the bare schema, though it doesn't detail format constraints like string length.

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 the tool performs 'semantic search using LanceDB vectors (Gemini embeddings)' and distinguishes it from keyword search, providing a specific verb ('search') and resource type ('vectors'). However, it doesn't explicitly differentiate from sibling tools like 'search_knowledge' or 'episodic_search' beyond the 'more intelligent than keyword search' comparison.

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 by mentioning it's 'more intelligent than keyword search,' suggesting when semantic search might be preferred. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like 'search_knowledge' or 'episodic_search,' nor does it mention any prerequisites or exclusions.

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