report_outcome

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

No annotations are provided, so the description carries the full burden. It discloses the learning side-effect ('自学', '生长/细化原型') and parameter meanings, but is vague about what 'reporting' entails (e.g., state changes, return values).

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 concise (a few sentences) and front-loaded with the main action. It efficiently explains parameter meanings, though the structure is somewhat informal.

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?

Given 7 parameters (3 required) and no output schema, the description covers parameter purpose but lacks details on return values, timing relative to other steps, and precise lifecycle context. It assumes familiarity with the system.

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 description coverage is only 14%, but the description explains observed_criticality, used_system2, and was_deep in detail, and clarifies the role of criticality_hint/difficulty_hint/progress. This compensates for the lack of schema descriptions on parameters.

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 clearly states the tool's action: report real outcomes after a step for self-learning. It explains specific fields (observed_criticality, used_system2, was_deep), but does not explicitly differentiate from sibling tools like decide_step or task_feedback.

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 implies usage occurs after a step ('这一步做完后') and recommends carrying over hints from decide_step. However, it does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives.

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