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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description adds substantial context the annotations cannot: the partial-update guarantee ('only the fields passed are touched') and a two-phase propose/confirm flow returning status='confirmation_required' with action_id and plan_token. It does not spell out what is at risk under destructiveHint (e.g., that a shortened description overwrites the prior text irrecoverably), which keeps it from a 5.

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?

Three sentences, each earning its place: scope first, then the partial-update invariant, then sibling routing, then the confirmation protocol. No restatement of the title and no filler.

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 correctly supplies the return shape for the unconfirmed path (status, action_id, plan_token), which is exactly the information an agent needs to chain into confirm_action. It is slightly incomplete for a 6-parameter tool in that the two required identifiers are never characterized and no validation or failure behavior is described.

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 0%, so the description carries the burden and only partly discharges it: it names four of the six parameters (title, description, priority, deadline) but says nothing about the two required parameters assignment_id and project_id, nor about the priority enum values or the deadline string format. The field list adds real meaning, but the required-parameter semantics are left entirely to the bare schema.

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 ('Change an existing assignment') and enumerates the mutable fields: title, description, priority, deadline. It also names the two sibling tools that cover the adjacent operations (reassign, status), so an agent can distinguish it from erp_reassign_assignment and erp_set_assignment_status without opening either 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?

Explicitly routes the agent away from this tool for reassignment ('use erp_reassign_assignment') and for lifecycle moves ('use erp_set_assignment_status'), and states the confirm_action condition under which the write actually lands. Both the when and the when-not are covered.

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