agent_start

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

With no annotations, the description carries the full burden. It usefully discloses that this kicks off an autonomous multi-step loop and that a DeepSeek planner decomposes and reviews steps when a key is configured and planning is on. It omits key behavioral facts: whether the call returns immediately or blocks, how progress/results are retrieved, and any cost or rate implications of the planner.

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?

Front-loads the purpose in four characters, then enumerates parameters compactly; no filler. The final sentence about DeepSeek planning is dense and slightly cryptic (it mixes planning trigger conditions into the same run-on structure), but it earns its place.

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 zero-parameter, no-output-schema tool, the description covers purpose, all arguments with types/enums/defaults, and the planner conditional. The remaining gap is lifecycle: it never says how the loop reports back or how it terminates, which matters for an asynchronous 'start' operation paired with agent_status/agent_stop.

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 input schema has no declared properties, so the description is the sole documentation, and it supplies real meaning: goal is required, provider takes jev/deepseek/local, max_steps is bounded 1-40 with default 20, and planner overrides the UI toggle. These enum values, ranges and defaults are exactly the semantics an agent needs and cannot get from 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?

States a specific verb+resource ('启动自主循环' – start an autonomous loop), which is clear and distinguishable from sibling agent_stop / agent_status by implication. It does not explicitly name those siblings, so differentiation is inferred rather than stated.

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?

No when-to-use or when-not-to-use guidance: nothing says to call this before agent_status to poll progress, or that agent_stop ends the loop. The DeepSeek planning clause describes internal behavior, not invocation guidance.

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