Control tasks

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the lower bar applies. The phrase 'every applicable task' usefully hints that some actions do not apply to all task states, but the description never says whether 'remove' is permanent, what happens to already-completed tasks, or whether partial failures are reported. It also leaves a mild tension with destructiveHint=false given that 'remove' implies deletion.

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 compact sentence with the action set front-loaded and the targeting rule following immediately; there is no filler wording.

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 three-parameter batch-mutation tool with no output schema, the definition is minimally viable. It covers targeting but omits what the call returns, whether invalid task_ids are ignored or error, and the permanence of remove.

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%, so the description must carry the parameter burden, and it only partly does. It clarifies the intent of task_ids (target individual tasks) and all=true (broadcast to all applicable tasks), but the action enum values are simply restated from the schema and mutual exclusivity of the two selectors is never stated.

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?

The description names specific verbs (pause, resume, retry, cancel, remove) against a specific resource (tasks), and the target selector (task_ids vs. all=true) is stated up front. It is unambiguous what the tool does, though it does not explicitly contrast itself with the read-only tg_tasks sibling.

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?

It implies usage by describing the two targeting modes (explicit task_ids, or all=true for every applicable task), which tells an agent how to call it. It gives no guidance on when to prefer one mode over the other, whether they are mutually exclusive, or when to use this versus tg_tasks/tg_wait_tasks.

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