update_reminder

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

Goes well past the destructiveHint=true annotation: it discloses that this is a full-replace update (fields not supplied are lost), that EventKit/Reminders access is required, that the API refuses a missing recurrence on repeating reminders, and that tags/subtask creation are impossible. These are exactly the behavioral facts an agent needs before invoking a destructive mutation.

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-loads the operation and the full-replace warning, then layers recurrence detail and constraints; every clause carries information. The telegraphic backtick-heavy fragments and mid-sentence line breaks make it slightly harder to parse than a plain prose version.

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 destructive 8-parameter mutation with an output schema (so return values need no explanation), the description covers the destructive semantics, permission prerequisite, id source, and the recurrence edge case that would otherwise cause silent data loss. Remaining gaps around non-critical scalar fields are minor at this complexity.

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?

With 0% schema description coverage the description does the heavy lifting for the risky parameters: ISO format and naive=local for due/start, the full RRULE grammar for recurrence including which clauses are refused, and the source of id. It leaves title, notes, priority and list_name unexplained, so the full-replace effect on omitted fields is not spelled out per parameter.

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 the specific verb and resource ('Update a reminder by id') and immediately qualifies the semantics with '(full replace)', which separates it from create_reminder, complete_reminder and delete_reminder in the sibling list. An agent knows exactly what operation this performs without opening the schema.

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 when-to guidance (recurrence is REQUIRED when the target repeats, and omission is refused so a rename can't kill the series) and explicit when-not limits (cannot set tags or make a subtask, no public API). It does not name sibling tools as alternatives for those unsupported operations, which is the only thing keeping this from a 5.

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