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

Annotations only supply destructiveHint=false, so the description carries most of the burden and does well: it discloses the login requirement, the Beijing-timezone interpretation of dates, the monthday overflow rule (超当月取月末), the assigneeId default of self, and the side effect that assigning someone else sends them a notification. It does not cover failure modes (e.g. invalid weekday/monthday combinations, missing goal permission) or what the returned "generated" list contains beyond a count, which keeps it from a 5.

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?

Dense, front-loaded and free of filler — the identity of the operation comes first, then per-freq constraints, then defaults/side effects, then sibling routing. The telegraphic semicolon style ("登录;") is efficient but slightly terse for non-Chinese-reading agents and leaves no structuring beyond punctuation.

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 9-parameter mutation with no output schema and thin annotations, the description covers the parameters that matter most (weekday, monthday, assigneeId, dates) plus side effects and sibling routing, so an agent could call it correctly. Minor gaps remain around goalId semantics, title/detail constraints, and error behavior.

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 only 22% (only startDate/endDate are described), so the description has to compensate — and it does for the three undocumented semantic parameters: weekday range and its WEEKLY binding, monthday range plus month-end clamping, and assigneeId's constraint (must be a collaborator of the goal, defaults to self). goalId, title, detail, and freq are left to the schema/enum.

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?

"建目标周期任务" gives a specific verb (创建) and resource (目标的周期/重复任务) scoped to a goalId, and it explicitly names the two sibling operations that operate on the same object (update_task_series, stop_task_series), so an agent can distinguish this from them without opening any schema.

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 states the precondition (登录), the conditional requirements per freq value (WEEKLY 须 weekday 1~7, MONTHLY 须 monthday), and routes the agent to alternatives: 改规则用 update_task_series, 终止用 stop_task_series. When-to-use, when-to-use-something-else, and mode-specific prerequisites are all present.

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