check_script_format

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

With no annotations, the description carries full behavioral disclosure, and it is richly transparent: it states it is free, pure rules, no model, no persistence, and repeatable. It discloses subtle behaviors beyond a simple 'check' — placeholder_left counts as an error because placeholders would be treated as image content, scene length counts only story-layer words excluding annotation lines, and strictOnly warnings become rejections in strict mode.

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 long but every section adds distinct behavioral value: error/warning categorization, placeholder explanation, scene-length counting rule, usage workflow, and limitation. It is front-loaded with the core purpose, uses bold and bullets to structure dense information, and avoids redundant phrases, though it could be slightly tightened.

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 there is no output schema, the description compensates well by explaining that issues are returned as a message list and how to use it (pass it back verbatim). It covers the main edge cases and constraints an agent needs to invoke the tool correctly, though the exact response structure is not specified and the strict-mode behavior is only partially detailed.

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 content parameter is already documented in the schema ('要检查的剧本正文(一次一集,上限 3 万字)'). The description confirms the parameter's role but adds no new semantics about format, limits, or accepted encoding beyond what the schema already provides, so a baseline 3 is appropriate.

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 with '回填前的格式自查' and states it runs script text through platform criteria and returns issues item by item, which is a specific verb+resource. It also explicitly delimits its scope against rewrite_script, saying '它只查格式', and lists exact error/warning categories, making it distinguishable from sibling tools like review_script and get_script_format_spec.

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 an explicit workflow: external AI finishes → run this tool → send the returned message list back → re-check → set_script, and clarifies this tool checks only format while fidelity judgments are left to rewrite_script. It also states when it is NOT appropriate (fidelity checks requiring original-side input), which is clear exclusion guidance.

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