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

Annotations only declare readOnly=false, destructive=false, openWorld=true. The description adds real behavioral context beyond that: the mutation also propagates to the linked ticket, and it enumerates the failure taxonomy plus idempotency/resend semantics for three terminal states. The error list is unstructured, but the recovery rules around filed_unrecorded and outcome_unknown are exactly the kind of safety detail annotations cannot carry.

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?

The core behavior is front-loaded in one clean sentence. However, the remaining text is an 18-item comma-separated error-code dump with no grouping, severity, or per-code meaning, which pads the definition without letting the agent act differently on most codes.

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 non-destructive mutation with no output schema, the description does cover the key side effect and failure recovery, which is the highest-value content. It still leaves gaps an agent needs: which permission/role is required (permission_missing and role_missing are listed but unexplained), and what assigning a null assignee_member_id does.

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 only 33%: due_date documents 'YYYY-MM-DD' but threat_entry_id and assignee_member_id are bare. The description says 'owner and due date' but never explains what assignee_member_id accepts, nor what a null assignee means (unassign? leave unchanged?). With low coverage, the description was expected to compensate and 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?

States a specific verb and resource ("Set the owner and due date of a threat entry") and adds the non-obvious side effect that the linked ticket follows. It is distinguishable from read-only siblings like get_threat_tickets, though it doesn't explicitly contrast with file_threat_tickets or sync_threat_tickets, which sound closely related.

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?

The retry guidance (don't resend filed_unrecorded/outcome_unknown without checking the tracker; resend not_attempted) is genuinely useful operational direction, but it only covers post-failure usage. There is no explicit when-to-use-this-vs-siblings guidance, particularly against file_threat_tickets and sync_threat_tickets which appear to touch the same ticket lifecycle.

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