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

Annotations already declare write-but-non-destructive (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the safety bar is lower. The description adds genuine context beyond that: the created object is a DRAFT rather than an active task, and it encodes a readiness gate ('sentence feels settled') before creation. It doesn't describe what is returned or the confirmation/approval round-trip, but the schema covers the latter.

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-loaded with the core action and scope, followed by the usage condition and then format guidance, in three tight sentences. The em-dash aside and the 'who decides what' clause are slightly conversational but each carries usable instruction rather than filler.

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 no output schema, the description still conveys enough to call it correctly: what is created, its draft state, the readiness condition, and the downstream compile step. Minor gaps remain — what the call returns (e.g., a task id needed for the subsequent compile) and the two-phase approvalId flow are left to the schema rather than narrated.

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 and the schema already documents all four parameters, including 'in the user's words.' The description partly repeats that phrasing, but it adds real semantic guidance the schema lacks: the sentence structure should be trigger-first ('When a claim arrives…'), then steps, branches, and decision ownership. That is actionable authoring guidance for the most important parameter.

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 + lifecycle scope ('Creates a DRAFT Task from a name + sentence'), which immediately separates it from the many sibling task operations (compile, start, freeze, update). The word 'DRAFT' plus 'then compile it' tells an agent exactly where this sits in the task lifecycle without opening another schema.

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?

Gives a clear readiness condition — use it 'once the user's sentence feels settled after you've refined it together' — and points to the natural next step ('then compile it'). It does not state what to do instead when the sentence is NOT settled (e.g., keep refining, or use update on an existing task), so there are no explicit exclusions.

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