knowledge_add

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

The description discloses a key behavioral trait: a failed write may be partial and recommends inspecting stage and file_id before retrying. This goes beyond the annotations, which only provide basic hints (readOnlyHint, idempotentHint, destructiveHint), adding practical failure-handling context.

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 sentences, front-loaded with the primary action and a useful warning. Efficient and to the point, with no wasted words.

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 is insufficient for an agent to correctly use the tool: it doesn't explain parameter semantics, doesn't specify the return structure (though no output schema exists), and lacks usage guidance relative to siblings. It only partially addresses failure handling.

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 description provides no information about any of the five parameters, despite the schema having zero description coverage. An agent would not know the purpose of title, source, metadata, or even that knowledge_id identifies the target knowledge base. This is a significant gap.

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 action: upload text, wait for processing, then attach to a knowledge base. It distinguishes itself from sibling tools by focusing on adding content, though it doesn't explicitly name alternatives.

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?

There is no explicit guidance on when to use this tool versus alternatives like knowledge_create or knowledge_update. The description implies usage for adding text to a knowledge base but doesn't mention any exclusions or alternative conditions.

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