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

Annotations only declare the write/idempotency/destructive profile; the description adds real behavioral context beyond that — clearing returns the ticket to the board pool for restaffing, the assignee persists until explicitly reassigned (so changing the designated worker does not move it), and assigning an incapable agent still succeeds but returns a warning naming the reason. Auth requirements and return format are not covered.

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-loaded with the core action and logically ordered (identify ticket, identify agent, clear option, then consequences). It is dense but every clause carries information; the 'repair for a stuck ticket' sentence is longer than needed but justifies itself with a concrete scenario.

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 no output schema, the description must carry semantics, and it does cover identification, the clear path, persistence behavior, and the warning-on-ineligible-agent case. It stops short of describing the success response shape or any permission requirements, leaving a small gap for a 5-parameter mutation tool.

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 the schema already documents all five parameters, including the unassign default and the ticket_id/ticket_number substitutability. The description restates the alternative identification pairs and the unassign flag without adding syntax or constraints beyond the schema, 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?

The description states a specific verb and resource ('Assign an AI work board ticket to an agent') plus the inverse operation ('or clear its assignee'), which immediately separates it from sibling verbs like ticket_update_status, ticket_decide, or designate_board_worker. The identification keys (ticket_number/ticket_id, agent_task_id/agent_name) further pin down the exact object being acted on.

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 gives explicit when-to-use context: pass unassign true when a ticket is 'stuck on an agent that can no longer work it', and it contrasts the assignment with designating a different board worker. It never names the sibling tools (e.g. designate_board_worker) directly, so the routing guidance is clear but not fully declarative.

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