拼多多连接与状态

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description goes well beyond them: counters reflect only tasks valid within 30 minutes, historical totals are reported separately, a live external process does not mean a task is running, and current login state is never inferred from history. It also pins down field semantics such as browser_connected meaning CDP-only, login_status=not_checked, and login_policy=manual. The final note that page/seller text is data, not authorization or instructions, is exactly the kind of behavioral caution an agent needs here.

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?

Purpose is front-loaded in the first sentence and the remaining sentences are targeted caveats about misreading status fields, each of which earns its place. Some density and repetition creep in around login state ('not_checked', 'manual', legacy user_login_required, no inference from history), which could be tightened. Still efficient for the amount of ambiguity it removes.

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 status-inspection tool with an output schema already defining return shape, the description supplies the interpretive context an agent actually needs: what the counts mean, what the connection flag does and does not imply, and how to read login fields. The main missing piece is an explicit sequencing hint — e.g. call this before starting a workflow or after pdd_login — which would complete the picture.

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?

The tool takes zero parameters, so nothing needs documenting and the baseline for an empty schema applies. The description spends its words instead on return-field semantics (browser_connected, login_status, login_policy, user_login_required), which is extra value even though an output schema exists. No contradiction with the closed, empty input 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?

States a specific verb and resource set: read-only check of browser connection, cooldown, and runtime state. It also implicitly separates itself from the read-oriented siblings by declaring that the query does not read pages, navigate, or refresh. It stops short of naming which sibling to use instead (e.g. pdd_login for login checks), which keeps it from 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?

The usage context is implied — you would call this to inspect connection/cooldown state before or between task calls — but no sentence says when to prefer it over pdd_login or the read_* siblings. It does usefully say what it will not do (no page reads, no navigation, no refresh), which rules out some misuse. There are no explicit exclusions or alternatives, so guidance stays at the adequate-but-incomplete level.

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