Schedule a job

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

Annotations are minimal (readOnlyHint=false, openWorldHint=false) and the description does not contradict them. The description discloses key behavioral traits: it requires the tool to be allowlisted, requires user confirmation (confirm=true), and warns against inventing entities. It also states the tool 'Enables publish_queue', indicating a side effect. This is useful context beyond the defaults, though it doesn't detail side effects like queue behavior or error 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 fairly concise, about 3 sentences, and front-loads the key purpose. It packs a lot of necessary information into a small space, though it is dense and might benefit from clearer separation of ideas. Still, it 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?

Given the tool's complexity (10 params, nested objects, no output schema), the description covers the essential call details: allowlist, confirmation, kind semantics, and the principle of using user-supplied ids. It doesn't document all parameters but the schema has some descriptions. There are minor gaps like how 'arguments' is structured or timezone defaulting, but overall it is adequately 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 only 30%, so the description must compensate. It explains the 'kind' parameter (once, every, cron) and the 'run_at' and 'every_ms' semantics partially: 'once (run_at ISO)', 'every (every_ms)'. It mentions 'cron (5-field)' and the confirm requirement. However, it does not explain parameters like 'name', 'timezone', 'max_runs', or the structure of 'arguments' beyond that they must be user-supplied. Since coverage is low, this is a moderate gap.

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's purpose: enqueue a future ads action on AdvisorPPC's queue because X is not natively capable. It identifies the specific verb 'enqueue' and the resource 'future ads action'. It distinguishes itself from siblings like x_ads_scheduler_setup and x_ads_schedule_list by emphasizing the scheduling of specific actions, though it could be more explicit about the difference between scheduling a write action and managing the scheduler infrastructure.

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?

Provides explicit guidance: the tool must be allowlisted with a list of specific tools, arguments must be user-supplied ids/status (never invented), and confirm=true is required after the user has specified time and entity. Also mentions enabling publish_queue as a prerequisite, which helps the agent know when to call setup tools. This is strong usage guidance.

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