save_kb_draft

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

Annotations already declare the write/idempotent/non-destructive profile, so the marginal contribution here is the draft lifecycle claim: 'Never published automatically.' That tells the agent the write is safe and staged, which is genuinely useful context not covered by the annotations. It still omits where the draft lands and what permissions or validation apply.

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 short sentences with the core action and the key constraint front-loaded; nothing is padded. The 'owner and suggested review date' clause spends words on fields the schema forbids (additionalProperties: false).

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?

With no output schema, the description should say what a successful call returns (draft ID, location, status) and it does not. Required-parameter semantics are only half covered. It is adequate to attempt a call but leaves the agent guessing about the result and about the phantom owner/review-date fields.

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 carries the burden, and it only partly does: 'current-policy sources' adds real meaning for the sources array, but title and body are never characterized, and no length or cardinality guidance appears. Worse, the mentioned 'owner and suggested review date' are not actual properties, so an agent may look for parameters that cannot be supplied.

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 verb+resource pair ('Write a knowledge article DRAFT') is specific and the phrase 'Never published automatically' narrows the intent well. It does not explicitly distinguish itself from the adjacent save_response_draft sibling, and it names an 'owner and suggested review date' that are not parameters, which slightly muddies the picture.

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 statement of when to use this versus search_knowledge, save_response_draft, or the other save_* siblings. The only implicit cue is 'with current-policy sources', which hints at a precondition but states no exclusions or alternative routing.

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