保存一步实验截图证据

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

The description discloses key behaviors: capturing a specified window, saving PNGs sequentially, and writing specific fields (stage, caption, parameters, window title, time, SHA-256) to an evidence list. This goes beyond the annotations (which only set all hints to false) and provides useful side-effect context. It does not cover every edge case but adds meaningful behavioral information.

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 a single sentence, action-first, with no filler. It efficiently conveys the tool's main actions and outputs while remaining concise and readable.

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?

With 7 parameters and no annotations, the description covers the core workflow (capture, save, log) but omits details about optional parameters like evidence_type and action_summary, and how session_id identifies the controlled window. Given the output schema exists, return values are already covered, but the description is not fully complete on its own.

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 must clarify parameters. It maps to stage_id (阶段), caption (说明), parameters, and window_title_contains (窗口标题), but leaves session_id, evidence_type, and action_summary unexplained. Time and SHA-256 are mentioned as outputs, not inputs. This partial compensation makes it adequate but not complete.

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 uses the specific verb '截取' (capture) with a clear resource ('受控 ENVI 窗口') and enumerates concrete outputs (PNG files, evidence entries with SHA-256). This distinguishes it from sibling tools like finalize_evidence or list_windows, making the purpose unambiguous.

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 for capturing step-by-step evidence, but it does not explicitly state when to use this tool versus alternatives (e.g., finalize_evidence) or mention prerequisites like an active session. It gives context but no exclusions or comparisons.

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