draft_form

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

With no annotations, the description does real work: it discloses a single model call (cost/latency) and, importantly, that human-written content is never overwritten, so the operation is safe to re-run. It stops short of saying whether the draft is persisted or merely returned, which is the key behavioral question for a tool paired with save_form.

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 tight clauses: what it drafts, what it produces, and the operational caveats (one model call, no overwriting of human input). Purpose is front-loaded and nothing is wasted.

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?

For a simple one-parameter tool, the description covers inputs and side-effect safety well, but with no output schema it should say what comes back — a draft payload to pass to save_form, or a saved record — and that gap leaves the agent unsure of the next step.

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% and the single 'saved_as' parameter already documents its origin in list_runs or build_ontology. The description adds no semantics about the parameter beyond confirming the run-scoped context, so the baseline of 3 applies.

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 gives a specific verb+resource (draft the object form / 起草对象表单) and enumerates exactly what gets produced: Chinese names for each object and field, a one-sentence description, and display fields. It implicitly contrasts with save_form via 'draft' vs. persist and the 'only human-writable columns' scoping, but never names the sibling explicitly, so an agent still has to infer the handoff.

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?

Usage is implied rather than stated: the tool is for filling in the human-only columns of a form, and the schema carries the prerequisite ('saved_as' comes from list_runs or build_ontology). There is no explicit when-to-use / when-not-to-use framing and no statement of what to do after drafting (presumably save_form).

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