发布环境自检

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

With no annotations, the description carries the full burden, and it does disclose a genuinely non-obvious side effect: verify_login=true actually launches a headless browser to validate the session, which signals real cost and external interaction. It also tells the agent the tool returns fix-it guidance rather than raw status. It does not describe behavior on partial failure or the exact return shape.

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?

Two short sentences with zero filler; the set of checks is front-loaded and the one behavioral caveat is appended where an agent will see it. Nothing could be cut without losing information.

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 one-parameter, no-output-schema diagnostic tool with no annotations, the description covers what is checked, what it returns, and the cost caveat of the verify flag. It is nearly sufficient, with only failure-mode behavior left unspecified.

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 100%, so the single parameter is already documented including its default. The description restates verify_login's effect, adding a little emphasis ('真开一次无头浏览器') but no new syntax or format semantics. Baseline 3 applies when the schema does the heavy lifting.

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 names three specific checks (cookies / browser driver / backend reachability) and states it returns remediation guidance, which is far more specific than the bare name 'get_publish_status' would suggest and prevents confusing it with an actual publish-report tool. It stops short of explicitly contrasting itself with siblings like batch_publish_chapters or set_tomato_cookies.

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?

Usage is only implied: the checks and remediation hints clearly position this as a preflight diagnostic before publishing, but the description never says 'run this before X' or when-not to use it. No alternative tool is named or ruled out.

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