run_analysis

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

No annotations are provided, so the description carries the full behavioral burden and does a good job: it discloses sync vs async execution per analysis kind, the one-task-at-a-time concurrency constraint, that WAV fixes NRD=20 and does not change the focal plane, and that MTF needs a caller-supplied frequency grid. It omits error/failure behavior and permission requirements.

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?

Front-loads the submission action and the returned status, then layers constraints per analysis kind. Dense but each sentence conveys a distinct constraint; no obvious padding.

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 an output schema present, return values need not be explained, and the description covers the key operational traits an agent needs (async vs sync, polling via get_analysis, single-task limit, WAV restrictions). Only some option-level parameter details are left to the schema.

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?

Reported schema description coverage is 0% for the top-level argument, so the description must compensate. It clarifies that native plots are selected via options.plot_type and that MTF frequencies must be supplied by the caller, but leaves ray_grid, azimuth, field_numbers, zoom_position and wavelength_numbers unaddressed.

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?

States a specific verb and the resources it submits (一阶参数、点列图、MTF、当前焦面 WAV、原生绘图) and notes it returns task status. It is distinguishable from get_analysis by being the submission step, but it does not explicitly name that sibling as the polling counterpart in the purpose statement.

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?

Gives concrete usage context: spot diagram and native plots are asynchronous and require polling get_analysis, while first-order, MTF and WAV complete synchronously; only one analysis task is allowed at a time; WAV is limited to single-zoom lenses over all fields/wavelengths. No explicit 'when not to use' or routing among siblings beyond the async note.

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