记录审阅状态

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 explicitly disclaims side effects (no author assignment, no notifications) and discloses the downstream gating effect on apply_plan. Gaps remain on whether existing states can be overwritten or whether transitions are validated (e.g. beautifying back to content_pass).

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?

Four short sentences, each carrying distinct information: state vocabulary, side-effect boundary, the apply_plan dependency, and the get/set split. No restatement of the tool name and no 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?

For a 4-parameter mutation tool with no annotations and no output schema, the description covers states, side effects, and the critical downstream dependency. It omits what action=get returns (the stored state and note) and any state-transition rules, which an agent would want before calling set.

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 75%, and the description adds real meaning beyond the bare enum by glossing each state value (content_pass/beautifying/rereview_pass) and by explaining that action=get is query-only. The undocumented parameter is pageId, whose meaning is left to inference, and note is only described in the schema.

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?

Uses a specific verb (记录/record) plus the resource (审阅状态) and enumerates the exact three allowed states with glosses, so the agent knows precisely what is stored. It also distinguishes itself from apply_plan by stating it only stores state and does not perform the actual write. It stops short of relating itself to the adjacent audit_* siblings, so not a 5.

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?

Gives a concrete precondition chain: without content_pass, apply_plan's real write is rejected, which tells the agent when this tool must be called first. It also clarifies the action=get branch as read-only. It does not say when NOT to use it or which state to pick in ambiguous situations (e.g. re-review after edits).

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