schedule_message

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

With no annotations, the description carries the full burden and does so: it explains that at fire time the message arrives as a new message in this chat, that the agent runs normally even with the phone locked, and that the user sees the pending item and can cancel it. The recurring-alternative note and the reminder-vs-agent-run distinction add behavior not captured anywhere else.

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?

Front-loaded with the core action and scope, then delivery mechanics, then the recurring alternative. Slightly padded by quoted examples and a parenthetical, but every sentence conveys something an agent needs.

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 5-parameter, no-annotation, no-output-schema mutation tool, the description covers delivery, lock behavior, user visibility, cancellation, and the recurring escape hatch. Minor gaps: what is returned (an id usable with cancel_scheduled) and the mutual exclusivity/timezone rules for the time parameters.

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% and the schema descriptions already explain at/in_minutes/quiet/remind in detail, so the baseline is 3. The body text reinforces when 'remind' applies and what the 'message' field should contain, but adds little syntax or constraint information (e.g. whether at and in_minutes are mutually exclusive) beyond 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?

States a specific verb+resource (schedule a message) plus scope: to yourself, in this chat, sent once. It also distinguishes one-shot from recurring by routing daily cases to 'Chat options > Schedule'. It never names the sibling tools that manage schedules (list_scheduled, cancel_scheduled), so the differentiation from those is left implicit.

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?

Gives concrete use cases (re-check something, remind the user, resume a task later) with an example, and an explicit exclusion: for something every day, tell the user about Chat options > Schedule. No guidance on inspecting or cancelling existing schedules, which the sibling cancel_scheduled/list_scheduled cover.

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