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

Goes well beyond the annotations: destructiveHint=true is already declared, but the description adds the crucial consequence that subtasks are cascade-deleted, the elevated permission requirement (FULL vs EDIT), the 204 response, and the required API-key scope `tasks:write`. That is exactly the extra context an agent needs before invoking a destructive call.

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 terse sentences, front-loaded with the action and immediately followed by the highest-risk fact (cascade delete). No filler, no repetition of the tool name, every sentence carries distinct information.

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, cascade operation with no output schema, it covers consequence, permission, response code, and scope. The remaining gap is what else is destroyed or orphaned — comments, attachments, time entries, relationships — and whether deletion is recoverable, which matters given the cascade.

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 `ref`, `account`, and `workspace` are all documented in the schema itself. The description only restates that deletion targets `ref` and adds no format or resolution detail beyond 'Task key or identifier', so the schema carries the load.

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?

Opens with a specific verb+resource ('Delete a task by ref') and the identifying parameter, so it is immediately distinguishable from siblings such as pm_delete_task_comment and pm_delete_task_relationship. Cascade behavior is stated in the same breath, further narrowing the meaning.

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?

Usage is implied rather than guided: the description never says when to prefer this over alternatives (e.g. pm_update_task to close/archive a task instead of destroying it) or how to obtain a valid ref (pm_search_tasks / pm_get_task). It does helpfully state the access prerequisite (FULL, not EDIT), which gives the agent a gating condition before calling.

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