触发视觉检测

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

The description goes beyond the idempotentHint annotation by detailing the trigger-to-analysis flow, the output file name, and the recommended polling delay. It could mention error handling or return behavior, but the output schema covers returns, and the timing hint is valuable behavioral context.

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 two sentences: the first states the action and effect, the second provides follow-up guidance. Every word earns its place, with no repetition of schema or annotation data.

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?

For a zero-parameter trigger tool with an output schema and a simple workflow, the description fully covers the tool's purpose, outcome, timing, and next steps, and references the relevant sibling tools. It is complete and actionable.

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?

There are zero parameters, so the schema coverage is trivially 100%. The description adds context about the default 'yanshe' mode, but since no parameters exist, the baseline of 4 applies.

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 sends a trigger command to the Hikvision vision host for default 'yanshe' diffraction detection, then writes results to a file. This specific verb+resource+mode distinguishes it from sibling tools like send_calibration and read_position_data.

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 explicitly instructs to wait 1-2 seconds before calling read_position_data to retrieve results, and directs users to send_calibration for calibration parameters. This provides clear sequencing and alternatives, making when-to-use obvious.

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