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

Annotations already indicate a non-read-only, non-idempotent, non-destructive operation. The description adds valuable behavioral details: default recipient (task assignees), default channel (push on), the constraint that at least one channel must be enabled, and the behavior of notify_if_completed. It also discloses that the response includes an app_url deep link.

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 concise, with three sentences that start with the primary action and then detail optional parameters. Every sentence adds functional value without repetition, making it easy to parse quickly.

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 nested object and multiple boolean channels, the description covers the key creation behaviors and even mentions the response's app_url. It doesn't explain error conditions or permissions, but these are not commonly required when the annotation and schema are present, and the description remains complete enough for basic invocation.

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?

The description enriches the schema by explaining practical semantics: remind_at is 'when to fire', recipient_id defaults to assignees, channel flags have a 'push on by default' and 'at least one must be on' rule, and notify_if_completed is clarified. However, it refers to task_id as a 'path parameter' while the schema nests it under body, which is a minor inconsistency that could confuse the agent.

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 'Schedule a reminder on a task' with a specific verb and resource, distinguishing it from sibling tools like update_reminders or destroy_reminders. It also names key parameters, making the tool's function unambiguous.

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?

The description implies usage by specifying parameters and defaults, but it does not explicitly state when to use this tool over alternatives or mention any exclusions. For example, it could say 'use update_reminders to modify an existing reminder' but doesn't, leaving the selection to be inferred from the name.

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