读取剧本内容和进度

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

Annotations already declare readOnly, idempotent and non-destructive, so safety is covered structurally. The description adds genuinely non-obvious context: fingerprints must be checked before editing, and 无任务不代表未知提交未发生 warns that an empty active_tasks list is not proof of a clean state. It does not describe staleness/refresh semantics or any rate or auth considerations, so it is useful but not rich.

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 front-loaded with what is returned, then moves to the safety-critical caveats, which is the right ordering. It is dense and telegraphic — some clauses (e.g. 核对 without stating what to compare against) are compressed to the point of ambiguity — but no sentence is redundant.

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?

An output schema exists, so return-value documentation is not required. Given a read-only, two-parameter tool, the description covers the risky edges: fingerprint verification before edits, stale task ambiguity, and the include_content truncation caveat. The only real gap is how this read differs from the episode-level and generic project reads in the sibling set.

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 0%, so the description carries the burden. It explains the meaningful consequence of include_content=false (truncated body that must not be used to overwrite full text), which is the key semantic an agent needs. project_id is left entirely to the obvious name, and the default interaction (default true) is only implicit.

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 a specific verb (读取) and resource (剧本), and enumerates what the read returns: 原生状态, active_tasks, 任务ID, 大纲, 分集, plus outline/episodes fingerprints. That is far more than a restatement of the name. It does not, however, explicitly distinguish itself from siblings such as pavo_script_get_episode or pavo_get_project, so an agent must infer the project-vs-episode 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?

It gives a concrete usage rule: 编辑前必须核对 (verify the fingerprints before editing), which tells the agent when this call is mandatory. It also states a restriction on include_content=false results. It stops short of naming alternatives for the episode-level or generic project reads, so there is no explicit when-not guidance.

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