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

Although annotations are absent, the description adds critical behavioral context by specifying that the deletion includes both the knowledge source itself and its associated vector embeddings. This defines the extent of the destructive operation.

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 definition is brief, direct, and front-loaded, providing all necessary information in a single, effective sentence without any fluff.

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?

While the description adequately defines *what* the tool does, it is incomplete for a destructive operation as it offers no safety warnings, prerequisite checks, or rationale for its existence compared to other maintenance functions.

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%, meaning the description must compensate. It does not define what 'bot_id' or 'source_id' represent (e.g., required format, ownership, or purpose), rendering the parameter definitions largely meaningless to the agent without external context.

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 provides a highly specific, action-oriented statement, using the verb 'Delete' and clearly identifying the resource ('knowledge source') and its consequence ('vector embeddings'). This is 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 offers no guidance on when to use this tool versus the many similar functions in the sibling set (e.g., list_knowledge_sources or purge_bot_knowledge). It fails to establish context or alternatives.

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