review_grade

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

No annotations are supplied, so the description carries the full burden. It does disclose that the write fans out to four targets (review queue, chapter status grid, event stream, _INDEX reconciliation), which hints at multi-effect mutation, but says nothing about auth requirements, reversibility, or what dry_run/sync_index actually change.

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?

It is extremely short, which is good in principle, but it is a compressed colon-plus-list fragment rather than a front-loaded sentence. Brevity here reflects under-specification rather than efficient communication.

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 7-parameter mutation tool with zero annotations, no output schema, no required-field guidance, and 43% schema coverage, a single telegraphic line is wholly inadequate. An agent cannot safely determine what will be written or under what conditions.

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?

Seven parameters with only 43% schema coverage, and the description adds no parameter meaning at all. The four undocumented ones (atom, note, dry_run, sync_index) leave the agent guessing about the key inputs, including whether dry_run prevents any mutation.

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 fragment '判定写回' does convey a specific action (writing a verdict back), and the following list names the targets touched. But the phrasing is telegraphic jargon with no sentence structure, and nothing separates it from siblings like review_due, learn_report, or kb_reconcile, which plausibly overlap with the review/queue/reconciliation domains.

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?

There is no indication of when this tool should be called instead of alternatives, nor any precondition, trigger, or exclusion. With siblings such as review_due and learn_report that could each be the right entry point for recording study outcomes, the absence of routing guidance is costly.

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