search_documents_vector

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

No annotations are provided, and the description gives no details about side effects, permissions, or return behavior. Since the tool is a search operation, it is reasonable to assume it is read-only, but this is not explicitly stated. The description also does not mention any edge cases (e.g., empty results, handling of malformed queries) which could affect the agent's expectations.

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 a single, concise sentence that captures the essential functionality. There is no unnecessary verbosity, and every word adds value. It is well-structured and easy to parse.

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 lacks crucial context about the tool's scope and expectations. It does not clarify what 'local research documents' refers to (e.g., a specific corpus, file types, or directory). It also does not hint at the output format, though an output schema exists. The missing parameter semantics and limited usage guidance leave the description incomplete for a robust agent decision.

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?

The schema provides no descriptions for the parameters (query and limit), and the tool description also fails to explain them. The description does not mention what constitutes a valid query (e.g., natural language vs. keywords) or what the limit parameter controls (e.g., maximum number of results). With 0% schema coverage and no description, the agent has no guidance on parameter semantics.

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's function: searching local research documents using vector-space ranking. This directly distinguishes it from sibling tools like search_documents (which likely uses keyword matching) and search_documents_semantic (which may use a different semantic approach). The verb 'search' and the specific ranking method make the purpose unambiguous.

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 does not explicitly state when to use this tool versus the alternatives. It implies that vector-space ranking is the differentiator, but there is no explicit guidance such as 'use this when you need semantic similarity' or 'use this instead of search_documents for fuzzy queries.' The sibling context provides some inference, but the tool description alone lacks clear usage instructions.

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