rpa_start_job

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

With no annotations, the description carries the full burden; it does disclose the return value (jobId) and a conditional approval prerequisite, which is meaningful behavioral context. It omits side effects, whether execution is asynchronous, what happens on parameter mismatch, and whether repeated calls create duplicate jobs.

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?

Three short sentences: action plus return value first, then the parameter-conformance rule, then the conditional approval requirement. No filler, and the most important constraint is front-loaded.

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?

There is no output schema, so naming jobId is helpful, but the description never explains that this starts an asynchronous job whose status must be polled elsewhere, nor does it cross-reference the policy or parameter-discovery siblings. For a job-launching tool with nested params and zero annotations, that leaves an operational gap.

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 75%, but the description adds genuine meaning beyond it: 'params' must conform to the target app's own input contract, and 'approved_by' is required specifically for fund-related or externally-sending apps, which the schema only phrases as 'apps on the approval list'. It says nothing about client_id (robot targeting) or explains app_id's semantics, so it is not fully comprehensive.

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 and resource ('启动一个影刀应用任务') and states the return value ('返回 jobId'), which is enough to distinguish it from read-oriented siblings like rpa_query_job and rpa_list_apps. It does not explicitly contrast itself with a sibling such as a hypothetical rerun/retry tool, so it falls short of a 5.

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 real usage constraint: the params must match the app's declared input definitions, and apps touching funds or sending externally require approved_by. However, it never says where to obtain those definitions (rpa_app_params) or the approval policy list (rpa_policy), leaving the agent to infer the workflow from sibling names alone.

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