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

Beyond the annotations (destructiveHint=true, idempotentHint=false, openWorldHint=true), the description discloses exact approval requirements, version concurrency control, retry replay limits ('completed effects cannot replay'), pause's inability to stop an executing provider call, and MCP-specific token behavior. This is rich operational context well beyond structured fields.

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 description is front-loaded with the core operations, then layers constraints and MCP-specific behavior in four tight sentences. Every sentence carries distinct operational information with no repetition or 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?

For a complex destructive mutation tool with no output schema, the description covers approval, versioning, retry constraints, pause limitations, and MCP execution semantics. Together with the annotations, it gives the agent everything needed to invoke the tool correctly.

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%, so baseline is 3, but the description adds useful semantics: 'Supply its current version' ties expected_version to concurrency, retry requires a failed idempotent local-read step (linking step_id to a specific condition), and confirmation_token should be omitted on the first MCP call. These go beyond the schema's field descriptions.

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 names the exact resource ('durable Operator task') and four specific control operations (pause, resume, cancel, retry), clearly distinguishing it from sibling read/list tools like get_operator_task and list_operator_tasks. An agent can identify its purpose immediately.

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 states critical usage conditions: exact approval, supplying the current version, the retry precondition of a failed idempotent local-read step, and the pause limitation. It does not explicitly name alternatives (e.g., use get_operator_task to inspect first), but the context and exclusions are clear.

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