add_knowledge

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

Annotations show readOnlyHint=false and idempotentHint=false. Description adds that content is chunked and embedded for semantic retrieval, plus return info (doc id, chunk count). No contradiction. Could mention potential duplication or overwrite behavior but not required.

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?

Three concise sentences, front-loaded with the verb, no redundant information. Every sentence adds value.

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?

Covers input format, processing (chunking, embedding), output (doc id, chunk count), and alternative tool. Lacks error conditions or permission requirements, but overall sufficient given the tool's simplicity and schema coverage.

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 coverage is 100% with clear parameter descriptions. Description only reiterates that content is chunked, adding no new parameter-level insight beyond the schema. Baseline score is appropriate.

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?

Description clearly states 'Import a document you provide...' and specifies the format (plain text/HTML). It distinguishes itself from the sibling add_knowledge_url by contrasting use cases.

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?

Explicitly tells when to use this tool ('when you already have the content') and when to use the alternative ('to fetch it from a web page instead, use add_knowledge_url').

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