trmnl_schedule_plan

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

With readOnlyHint/idempotentHint already declaring safety, the description adds genuinely non-obvious behavior: the tool produces text, not a schedule, and the harness is responsible for actually registering and verifying the automation. That is exactly the kind of side-effect expectation an agent would otherwise get wrong. It still doesn't describe the shape of the returned prompt/command.

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?

Two tight sentences with the capability first and the critical limitation second — no filler. Slight loss for jargon ("host-native", "portable CLI command") that is never unpacked.

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 tool whose only output is generated text, and which has no output schema, the description should say what the caller receives and how to consume it. Combined with zero parameter documentation, the definition leaves the agent unable to fill in the arguments or act on the result 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 description coverage is 0% for three parameters (id, harness, timeZone), so the description must compensate and does not. Nothing explains what `id` identifies, that `harness` selects the target host dialect, or how `timeZone` influences the emitted prompt.

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?

It names an action ("prepare") and two artifacts (a host-native scheduling prompt and a CLI command), and explicitly excludes automation creation. But it never says what is being scheduled or what the `id` refers to, so the agent cannot confidently map it to a resource — especially against siblings like trmnl_get_playlist_item_schedule and trmnl_replace_playlist_item_schedule.

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?

"This tool does not create an automation; the harness must use its scheduler and verify it" gives a useful negative constraint and an implied workflow (call this, then schedule externally). It does not say when to prefer this over the sibling schedule tools, nor what a caller must do with the result.

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