即梦实际接口能力

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds value by stating the payload contents and the important caveat that being callable does not mean real generation has been validated. That caveat about data trustworthiness goes meaningfully beyond structured fields; only the exact response shape is left implicit.

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 dense clauses: the first front-loads what is returned, the second gives the ordering instruction and the reliability caveat. Every clause earns its place, though the telegraphic phrasing is compressed enough to require careful reading.

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 zero-parameter discovery tool with no output schema, the description should convey enough about the returned structure to act on, and it only lists categories without shape. The missing piece is a disambiguation line against action_schema and studio_catalog, which also expose implementation metadata.

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 tool takes zero parameters, so there are no semantics to explain and the baseline is 4. Nothing in the description contradicts or wastes space on parameter framing.

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 names concrete resources: implemented operations, a read-only switch, and a credit cap, so an agent can tell this is a capability-introspection tool rather than a job runner. It does not, however, distinguish itself from sibling discovery tools such as action_schema or studio_catalog, leaving overlap unresolved.

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?

'先查能力再执行' gives an explicit call-ordering rule: query this before invoking anything else, which is real usage guidance. It stops short of exclusions or naming which sibling to use when, so the agent must infer boundaries versus action_schema.

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