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

Annotations already mark destructiveHint=true and openWorldHint=true. The description adds the critical 'once; never replay' constraint and the reply format ('results, not approval handles/JSON/debug'). This is valuable behavioral context beyond the annotations, especially for a destructive, irreversible operation.

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 three short, front-loaded sentences. Each sentence serves a distinct purpose: what it does, when to use an alternative, and what output to expect. No filler or redundancy.

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?

Given the output schema exists, return values are covered. However, the input parameters are under-specified. An agent may not know what a valid expected_plan_digest is or how to obtain it. The non-replay and lost-token guidance add context, but the missing parameter semantics leave a gap.

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 must compensate. It merely lists the parameter names ('approval_ref + expected_plan_digest') without explaining how to obtain them or their exact meaning. The pointer to operations_get_approval for a lost token partially helps with approval_ref, but expected_plan_digest remains unexplained.

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 states a specific action ('Confirm launch'), the precondition ('after explicit approval'), and the one-shot nature ('once; never replay'). It also distinguishes itself from operations_get_approval for the lost token case, making the tool's purpose clear and distinct from the many sibling approval-related tools.

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 gives clear context: use after explicit approval, never replay, and if the token is lost use operations_get_approval. It implies when not to use (e.g., denial tools) through naming, but does not explicitly mention alternatives like operations_deny_approval. Still, the guidance is strong.

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