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

Goes well beyond the destructiveHint=true annotation by describing exactly what is destroyed versus retained: in-flight runs stopped, a waiting gate closed, schedule trigger halted, past runs kept in history. It also warns that the call may return needs_confirmation, which is real behavioral context an agent needs.

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?

Four short sentences, front-loaded with the core action and effect, then the pre-check guidance and the confirmation note. Dense and largely waste-free, though the parenthetical about the gate is a slight tangent.

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 destructive three-parameter tool with no output schema, the description covers the mutation effects, the pre-call verification step, and the possible confirmation response. An agent has everything needed to invoke it correctly.

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%, so taskId, workspace, and approvalId are already fully documented in the schema. The description only indirectly adds meaning by explaining the needs_confirmation/approvalId loop, 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?

States a specific verb and resource ('Deletes a task') and immediately clarifies the effect scope: in-flight runs stopped, schedule trigger stops, past runs preserved. This distinguishes it implicitly from pause-like siblings such as workbench_tasks_freeze, though no sibling is named directly.

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 an explicit pre-flight condition: check workbench_tasks_get for live runs and disclose them before proposing deletion. It also signals the confirmation flow, but it does not name a non-destructive alternative (e.g. freeze) for when the agent should not delete.

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