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

Annotations already declare destructiveHint=false and readOnlyHint=false, so the description adds genuine value by spelling out what pausing means: the workflow halts autonomous execution, no data is removed, and the state is resumable. It does not clarify what happens to runs already in flight, which is the main remaining behavioral unknown.

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?

Two short sentences with the core action front-loaded and the reversibility caveat immediately after. No filler and nothing that could be cut without losing information.

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 single-identifier mutation with annotation coverage and no output schema, the description covers action, side effects, and reversibility. The only gap is the fate of currently executing runs, which an agent might reasonably want to know before calling.

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 100% and the parameter description already explains accepting an id or a name from list_workflows; the tool description adds nothing further about the identifier. Baseline 3 applies since the schema carries the full burden.

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+resource (pauses a workflow) and clarifies the effect — it stops running on its own — plus a contrast to deletion ('Nothing is deleted'), which indirectly distinguishes it from delete_workflow in the sibling set. However, the name 'stop_workflow' and the title/description 'Pause' are not reconciled, and the sibling start_workflow/run_workflow are never named, so a small amount of inference remains.

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 clause 'Nothing is deleted and it can be started again' implies when to prefer this over delete_workflow, but the guidance is implied rather than stated. There is no explicit 'use this instead of X when Y' routing, and pause_campaign in the sibling list isn't referenced.

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