列出 DSH 任务

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds what the summary records contain and the polling use case, but says nothing about ordering ('最近' is not defined), pagination, or what happens when no tasks exist.

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 field list in parentheses; no filler. Slightly dense with the field enumeration but every element carries 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?

With two optional params, no output schema, and full schema coverage, the description adequately conveys scope and return fields. It still omits ordering guarantees and default behaviors that matter for a polling-oriented list tool.

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%: 'limit' (1-100, default 20) and the status enum are fully documented in the schema. The description adds no additional meaning about filtering or limit behavior, so the baseline 3 applies.

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 and resource ('列出最近的任务摘要') and enumerates the returned fields (task_id / 状态 / 预览 / cwd / 时间 / 错误), which clearly separates it from single-task siblings. It never names dsh_status or dsh_result, so sibling differentiation is only implicit.

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 phrase '用于回顾历史与继续轮询' gives an implied context for use (history review, polling), but no explicit when-not-to-use and no reference to the alternative tools (dsh_status for one task, dsh_search for querying). An agent must infer the choice from sibling names alone.

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