uplus_patrol

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

With no annotations, the description carries the burden well: it discloses the report artifact, the categorization it performs, and crucially the safety boundary that subjective, programming and file items are never auto-submitted. It still omits where/how the Markdown report is written (overwrite semantics) and says nothing about what auto_answer triggers, which is a second potentially side-effecting flag.

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-loaded with the core action, then the elaboration, with no filler sentences. The second sentence is dense with slash-separated categories but every clause carries information.

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 multi-course orchestration tool with side effects and no output schema, the description covers the classification and submission policy but leaves gaps: no return/report location, no statement that auto_answer may perform write actions, and no note about login prerequisites given the uplus_login/uplus_check_login siblings.

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 0%, so the description must compensate and it only partially does. 'submit=True' is explained with real semantics plus exclusions, but the second parameter auto_answer is not mentioned at all, leaving one of two flags undocumented anywhere.

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?

Opens with a specific verb+resource+artifact: 'Patrol every configured course and write a Markdown report.' The second sentence enumerates the aggregation behavior (homework + experiments, submitted/pending/outstanding/takeover, answer briefs), which clearly separates it from the narrower siblings like uplus_list_homeworks and uplus_inspect_homework.

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?

Usage is implied (run a sweep across all courses once logged in) but never stated as when-to-use versus the individual list/inspect tools. The only explicit guidance is the conditional 'submit=True only submits homework that received valid answers', which is a behavioral guardrail rather than routing guidance.

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