继续

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

Annotations only give the three hints (readOnly=false, idempotent=false, destructive=false). The description adds genuinely useful behavior beyond them: Range-based resume when possible, full re-download otherwise, the restarted=true marker, and a ~30s plugin cold-start latency. It does not explicitly warn about partial-state side effects, so not a 5, but it clearly exceeds the annotation baseline.

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?

A single front-loaded sentence with the action and its fallback semantics packed into a parenthetical, plus one short latency note. No filler, though the parenthetical is dense.

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 resume tool with no output schema, the description covers the key operational uncertainty (resume vs restart, cold-start latency) and the restarted=true signal. Its main gap is the complete absence of parameter guidance for jobId/stateDir, which an agent needs to invoke it correctly.

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 0% and the description says nothing about either parameter. jobId (the required identifier) and stateDir (the optional state location) are left entirely undocumented, so the description does not compensate for the coverage gap.

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 (继续/resume) and resource (一个被暂停/中断的任务), so the agent knows exactly what operation is performed. It is distinguishable from sibling pause/cancel/status by its action, though it does not name those siblings explicitly.

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 description scopes the trigger condition to "被暂停/中断的任务" (paused/interrupted tasks), which implies when to use it. However, it never names alternatives (e.g. chrome_download to start fresh vs this to resume) or states any exclusion, leaving routing to inference.

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