Hand another session a tracked task

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

With no annotations, the description carries the full burden and does much of it: it discloses the notification lifecycle (accepts/progresses/finishes/fails), the default 24-hour expiry, and the delivery path for a Claude session. It omits permission/auth requirements and what happens if the assignee never responds, but the lifecycle transparency is well beyond a typical 'create task' blurb.

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?

It is front-loaded with the core action and packs substantial information into three sentences with no filler. The middle sentence is long and carries three clauses (lifecycle, expiry, Claude-session delivery), which makes it denser than ideal but not wasteful.

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 mutation-style tool with eight parameters, no annotations and no output schema, the description covers return behavior (what you are notified about), expiry defaults, and per-parameter intent well enough to call it confidently. Remaining gaps are edge cases (unaccepted tasks, permission requirements) rather than anything needed for a correct invocation.

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 already 100%, so the 3 baseline applies, but the description adds real guidance on two parameters: 'Say what done looks like in acceptance_criteria' clarifies the expected content, and 'Use risk high only for work that must not wait' gives a use policy for the enum that the schema's 'delivered as urgent' does not.

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 pairs a specific verb+resource ('Give another agent session a task') with the defining trait that separates it from send_message/ask: the task is 'tracked' and 'you are told when it accepts, progresses, finishes or fails.' An agent can distinguish this from the fire-and-forget messaging siblings without opening any 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?

It explains the delivery mechanics ('For a Claude session the task is created and tracked, and you are given the message to send with your built-in SendMessage') and gives one conditional rule ('Use risk high only for work that must not wait'). However, it never explicitly states when to choose send_task over ask or send_message, leaving the sibling selection to inference.

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