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

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the description correctly implies a write operation without destruction. It adds valuable behavioral context: the target op is invoked with empty input, duplicate Routines are rejected, and there are hard caps (3 per app, 25 per user). This goes beyond the structured annotations and helps the agent anticipate side effects and failure conditions.

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 compact, two sentences, and front-loads the primary use case before detailing constraints. Every sentence contributes: the first defines the scenario, the second explains mechanics, input requirements, and limits. There is 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?

The tool has an output schema (indicated by 'Has output schema: true'), so return values are covered there. The description covers the key aspects an agent needs: when to use, allowed intervals, the empty-input requirement, duplicate rejection, and caps. For a creation tool with clear schema and annotations, this is 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?

Schema coverage is 100%, so each parameter (app_id, op, interval) is already described. The description adds meaning by clarifying that interval accepts only 'hourly', 'daily', or 'weekly' and explicitly rules out cron syntax. It also explains that the op is called with empty input, which informs the agent that op must not have required fields—a semantic detail not present in the schema.

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 creates a Routine that schedules an app op on a timer, and distinguishes it from chat-based operations. It specifies the verb 'schedules' and the resource (an app's declared op), and the opening phrase 'Use this when the user wants an app op to run on its own, on a timer' immediately clarifies the primary use case, setting it apart from siblings like update_routine or delete_routine.

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 gives a clear trigger condition ('when the user wants an app op to run on its own, on a timer') and explicitly notes it is not a chat operation. It also states constraints like 'no cron syntax' and that the op must not have required input fields, which guides correct usage. However, it does not explicitly mention when to use an alternative tool (e.g., update_routine to modify an existing Routine), though this is implied.

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