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

Goes beyond the annotations by clarifying that the operation is a soft archive ('Nothing is deleted') with a known undo path, which materially reframes destructiveHint=true. It also discloses the approval-gating requirement, something annotations cannot express. The only gap is that 'call without approved to see what happens' does not say what that call actually returns (a preview, an error, a confirmation prompt).

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 short sentences, each carrying distinct information: what it does, that it is reversible, the prerequisite, and the approval protocol. Nothing is repeated from the name or annotations, and the outcome is front-loaded.

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 two-parameter, no-output-schema mutation tool, the description covers reversibility, prerequisite ordering, and the human-approval gate, which is what an agent needs to call it safely. Minor incompleteness remains around what the unapproved call returns and what workflow_id accepts.

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 50%: approved is documented in the schema, workflow_id is not. The description adds real meaning to approved by defining the sequencing semantics (preview call first, confirmed call second), though it says nothing about workflow_id or accepted identifier forms, which the schema also leaves blank.

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 plus the resulting state ('Move a workflow to Archived'), and anchors it to a familiar analogue ('like the dashboard's Archive'). It also implicitly separates itself from restore_workflow, which is named as the inverse operation.

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?

Gives an explicit prerequisite ('Pause its schedules first (pause_schedule)'), names the reversing alternative (restore_workflow), and prescribes a two-phase call pattern: call without approved first, then with approved: true only after human confirmation. When-to-use, ordering, and exclusions are all covered.

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