ue5_task_begin

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

With no annotations, the description carries the full burden; it does disclose the important singleton constraint ('one active task at a time') and the closing tool, plus that the dashboard renders from this data. It does not state whether the call fails or overwrites when a task is already active, nor what identifier or payload comes back.

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, front-loaded with the action and ending with the constraint and next step; nothing loops or buries the lede. Slight redundancy in echoing field names already in the schema, plus bilingual duplication, keeps it off a 5.

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 6-parameter stateful tool with no annotations and no output schema, the agent still doesn't know the failure mode on a second concurrent declaration or what the call returns. The lifecycle framing is present but behavioral edges are not covered.

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 coverage is 100%, so the baseline is 3. The description merely re-lists field names (goal, asset, understanding, approach, steps) that the schema already documents, and notably omits user_request, the one parameter whose purpose (verbatim user words for a 原话 vs 理解 comparison) would benefit from emphasis.

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?

Clear specific verb+resource: 'Declare a task for the dashboard' with an enumeration of the fields it carries. It also names the terminating sibling (ue5_task_end), so the agent can place it in the task-lifecycle family rather than confusing it with ue5_task_list or ue5_task_step.

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?

'One active task at a time; close with ue5_task_end' gives both a usage constraint and the explicit follow-up tool. It lacks an explicit 'use when starting multi-step work' trigger and doesn't say what to do if a task is already open, but the sequencing rule is clear.

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