get_prepared_action

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds the specific constraint that it never executes the action, which is beyond the generic read-only hint. It also introduces the 'unexpired' condition, adding useful context about expiration behavior.

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 a single sentence that packs the core purpose, scope, and a key constraint without any redundancy. Every word earns its place.

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 strong annotations and a simple one-parameter design, the description covers the essential behavior. It doesn't detail return values, but no output schema exists and the tool's purpose is straightforward, so the description is sufficiently complete.

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?

The schema has zero description coverage for the single parameter confirmation_id. The description doesn't explicitly define it, but the tool name and description ('prepared action') strongly imply it is the ID of a prepared action. For a single self-explanatory parameter, this is adequate, though it could have been more explicit.

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 clearly states the tool reads prepared actions and never executes them, which directly distinguishes it from execution tools like execute_confirmed_action. The verb 're-read' and 'retrieve' precisely communicate the read-only nature.

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 description provides an explicit when-not instruction ('Never executes it') and indicates usage for re-reading or retrieving results of unexpired prepared actions. It doesn't explicitly name alternative tools, but the sibling names (e.g., execute_confirmed_action, cancel_prepared_action) make the contrast clear.

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