novel_fix_plan

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

With no annotations, the description carries the behavioral disclosure burden and does disclose key traits: the plan/verify/mark semantics, the composition of each plan item, and the hard constraint that no actual sentences are generated. It implies mark is a state change, but it does not state whether changes persist or what side effects occur, which prevents a higher score.

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 dense sentences front-load the core purpose, then the action semantics, then the decisive boundary. There is no filler and no repetition of what the input schema already states.

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 the moderate complexity of six parameters, three actions, no annotations, and no output schema, the description covers the plan output structure, action behavior, and inter-parameter relationships well. It does not specify the exact return shape of verify or error handling, but the schema covers individual parameter definitions.

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%, so the baseline is 3, but the description adds meaning by defining each action value, declaring plan as the default, and stating that mark requires both itemId and state while sourcing itemId from plan's returned items[].id. This goes beyond the plain schema property descriptions.

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 opens by stating that the tool converts style diagnosis into a prioritized todo list, and enumerates exactly what each item contains (sentence position, current/target values, anchor passage, revision direction). It differentiates itself from siblings by declaring '只给方向不给句子' – it gives direction, not prose – which is a clear distinguishing boundary.

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 gives concrete per-action usage: plan generates the checklist and is the default, verify re-tests the current text, and mark requires both itemId and state. It also states the negative case (does not generate prose), but it does not name alternative sibling tools or specify the exact workflow ordering relative to style_check.

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