MK 批量完成课程

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

With no annotations, the description carries the full burden and does well: it discloses built-in ≥13s write throttling, rate-limit retry, deliberate wrong-answer behavior for quizzes, PDF byte download, and that discussion tasks return a list instead of executing. It omits idempotency/re-run semantics, auth prerequisites, and the fact that defaults (onlyUnfinished=true, dryRun=false) mean it will actually write.

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?

One dense paragraph, front-loaded with the action and then the per-type rules; nearly every clause carries operational information. Slightly cramped and mixes batch policy with execution timing details that could be split, but there is little waste.

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 the description should characterize what comes back; it only describes the discussion-list return case and is silent on what success/failure output looks like for videos, documents, and quizzes. For a batch mutation tool with throttling and retries, that leaves meaningful gaps around partial failures and re-run 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 33%, so the description must compensate. It does add real meaning for the ct codes (1/3/4/5/6) and for autoQuiz's simulated answering, but dryRun, onlyUnfinished, and includeUnpublished are documented nowhere, leaving three behaviorally important parameters unexplained.

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+resource ('批量完成任务点') and then enumerates the exact per-content-type behaviors (ct1 video, ct3 PDF download, ct4 rich text, ct5 quiz, ct6 discussion). This clearly distinguishes it from the single-item sibling mk_complete_unit and routes discussion work elsewhere.

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?

Explicitly says discussions are NOT auto-posted and that the agent must follow up with mk_discuss_reply at ~30s intervals, which is real when/how guidance tied to a named sibling. It doesn't state when to prefer this tool over mk_complete_unit (single unit) or how dryRun/onlyUnfinished should drive the decision, so it falls short of full when/when-not coverage.

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