save_extracted_knowledge

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

No annotations are provided, so the description must fully disclose behavior. It states persistence and gives input/output structure, but it does not mention side effects like whether existing entries are overwritten/appended, whether mutations are reversible, or any permission requirements. This is a moderate gap for a write 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 description is front-loaded with the core purpose, then the usage workflow, then arg/return details. Every sentence adds value, and it is succinct without unnecessary verbosity.

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 tool has an output schema, so return details are optional but provided. The description covers the workflow, input structure, and resource destination. It could be more complete by noting behavior on repeated saves (append vs overwrite), but for a persistence tool of confirmed entries, it is largely sufficient.

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 0%, so the description must compensate. It does so thoroughly by explaining design_id as the source design ID and specifying the exact required keys (key, content, category, affects_columns) for each entry dict, adding meaning well beyond the bare schema.

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 states a specific verb ('Persist') and resource ('user-confirmed knowledge entries to extracted_knowledge.yaml'), making the tool's purpose unmistakable. It also distinguishes from siblings like save_review_comment/save_review_batch by focusing on knowledge entries rather than review comments.

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 explicitly instructs to call extract_domain_knowledge() first, then pass confirmed entries here, providing a clear workflow and prerequisite. This effectively tells the agent when to use this tool (after extraction) and implies it is for confirmed entries only.

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