uplus_patrol

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

With no annotations, the description carries the full burden and discloses meaningful behavior: it distinguishes submitted/pending/outstanding/takeover items, collects objective questions for the client model, tries built-in auto-answer rules only when auto_answer=True, and restricts submit=True to homework with valid answers while never auto-submitting files or subjective items. It does not disclose prerequisites such as login state, whether submissions are reversible, or where the Markdown report is saved.

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 front-loaded with the core action and then uses three tightly scoped bullets. Every sentence adds useful behavioral or parameter context, and there is no repetition or filler.

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?

Given the absence of annotations and an output schema, the description covers the behavioral flow well: discovery, classification, answer briefing, auto-answer fallback, and submission constraints. It is still missing some information an agent might need, such as the report's return value or save location and any authentication prerequisite, so it is strong but not fully complete.

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%, but the description fully explains both boolean parameters. auto_answer is defined as trying built-in rules first with unanswerable items remaining in takeover, and submit is defined as submitting only homework that received valid answers, with file and subjective items excluded. This adds substantial meaning beyond the bare parameter names.

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 states a specific verb and resource: 'Run a full patrol over configured courses and save a Markdown report.' It then enumerates the key sub-actions (listing homeworks/experiments, building an answer brief, submitting valid answers), making clear this is an aggregate orchestration tool rather than one of the sibling list/inspect tools.

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 clear context for when to use it: a full patrol across configured courses, with explicit behavior for the submit and auto_answer options. However, it does not explicitly name alternatives like uplus_list_homeworks or uplus_inspect_homework, nor does it state when not to use this aggregate sweep.

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