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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the description's 'Read-only' mainly repeats structured data. It does add useful context about the returned attributes (message, time, enabled state, creator), but it omits any mention of ordering, pagination, or what happens when no reminders exist.

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 front-loaded sentence plus a short safety note; every clause adds information. The trailing 'Read-only' is somewhat redundant given the readOnlyHint annotation, but it is brief and not harmful.

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 no-parameter, read-only listing tool the definition is close to sufficient, and the parenthetical explanation of reminders is a helpful disambiguator. However, with no output schema it should specify the return structure more concretely, and it should mention behavior when the list is empty.

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?

There are zero parameters, so there is no parameter ambiguity. The description's field-level summary ('what each says, when, whether it is on, and who set it up') gives useful meaning to the implied return shape, though no output schema exists to formalize it.

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 states a specific verb ('list') and resource ('reminders'), and clarifies what a reminder is ('notifications on their phone'). It also enumerates the returned fields (text, time, enabled state, creator), so an agent can distinguish this from sibling tools like trainrec_set_reminder.

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?

Usage is implied rather than stated: 'The person's reminders' signals a retrieval of all reminders with no filtering, and 'Read-only' implies it must not be used to change reminders. However, it does not explicitly point to trainrec_set_reminder for creation or trainrec_delete_reminder for removal.

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