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

The description goes well beyond annotations by disclosing a non-obvious behavioral trait: moving a reminder to a list in a different account recreates it, changes its id, and returns id_changed, new reminder_id, and previous_reminder_id. It also gives a critical follow-up instruction to always take reminder_id from the response. Annotations only set readOnlyHint=false and destructiveHint=false, so this is additive, not contradictory.

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?

Three purposeful sentences: purpose first, then prerequisites, then a clear warning about a critical edge case. No filler, every sentence earns its place, and the most important operational caveat is prominently flagged with 'IMPORTANT'.

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 a complex 7-parameter mutation with an output schema, the description covers prerequisites, mandatory confirm, parameter effects, a cross-account recreation edge case, and the required follow-up behavior. No critical guidance an agent needs to invoke the tool correctly is missing.

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 baseline is 3. The description adds operational meaning beyond the schema by stating that confirm=true is required, that reminder_id comes from list_reminders, and by reinforcing the id-changing consequence of list_name. This elevates it above baseline, though the schema already documents most parameter details.

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 uses a specific verb ('Updates'), identifies the resource ('existing reminder in Reminders.app'), and enumerates the modifiable fields. The word 'existing' plus the instruction to get reminder_id from list_reminders clearly distinguishes this from create_reminder and complete_reminder, even without naming them.

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?

Provides clear operational context: use it to update an existing reminder, obtain reminder_id from list_reminders, and set confirm=true. It doesn't explicitly state when not to use it or point to alternatives, but the 'existing reminder' scope and field list make the applicable case unambiguous.

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