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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the key operational fact that approval happens client-side before execution, telling the agent not to re-confirm in chat. It also reinforces permanence ('cannot be undone'), which is implied but usefully restated.

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 action and scope, then adds the permanence warning and approval behavior. It runs a bit long with three sentences, but each carries actionable information rather than filling space.

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 an output schema present and full parameter coverage, the description supplies the remaining operational context (permanence, external approval, project vs personal) that an agent needs to call it correctly without over-confirming.

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% and the schema already documents taskIds and the projectId omit-for-personal behavior, so the description adds little beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 ('Delete') and resource ('tasks by IDs') and immediately clarifies the projectId vs personal-task scope, which distinguishes it from page-deletion siblings like xtiles_delete_page.

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?

Explicitly tells the agent when to act versus ask: 'when the user has named what to delete, delete it rather than asking again; ask only when you cannot tell WHICH item they meant.' It also names the projectId condition for project vs personal tasks.

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