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

With no annotations, the description carries the full burden and does well by disclosing key behaviors: it notes that delete is a soft-delete, restore exists, and 'complete' advances recurring reminders to the next occurrence. It also hints at soft-delete behavior via the 'include_deleted' parameter. Missing details like return values or error handling, but those are not required given no output schema.

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 front-loaded summary followed by a tight bullet list, one per action. Every sentence is directly useful, no fluff or repetition. It is well-structured with consistent formatting, making it easy to scan and understand.

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 with 7 actions, 12 parameters, no annotations, and no output schema, the description covers all actions and parameter requirements, including edge cases like soft-delete and recurrence. It stops short of explaining pagination defaults beyond naming 'page' and 'per_page', but those are in the schema. Overall, it is complete enough for an agent to select and invoke the tool correctly for most scenarios.

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%, so the baseline is 3, but the description adds significant meaning by mapping parameters to specific actions (e.g., contact_id is 'required for create, optional filter for list'). It also clarifies the semantics of frequency and the recurring reminder behavior on 'complete', which goes beyond the schema's straightforward descriptions. This helps an agent construct valid requests per action.

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 opens with 'Create, list, update, complete, snooze, delete, or restore reminders,' which specifies the exact verbs and resource, making it clearly distinct from sibling tools like task_manage or activity_manage. Each action is enumerated with precise scope, leaving no ambiguity about what the tool does.

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 provides clear context for when to use each action by pairing them with required parameters (e.g., 'Requires id and new_date' for snooze). While it doesn't explicitly name alternative tools or exclusion criteria, the action-specific breakdown gives an agent enough guidance to select the right action and avoid misuse. Sibling tools target different resources, so the intended usage is implied.

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