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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, openWorldHint=false, idempotentHint=false). The description adds real context beyond them: the request_key is single-use and a changed intent under the same key fails, and the write requires a confirmed intent. The one-time-key semantics sit in mild tension with idempotentHint=false (no key means repeat calls do create duplicates), but this is a request-level dedup guard, not a flat contradiction.

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?

Two sentences, both front-loaded: the action and its precondition come first, the key constraint second. Nothing is padded or repeated from the schema.

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 6-parameter destructive write with a two-step confirmation flow, the description covers the confirmation gate, the key constraint, and the target scope. It omits the mechanics of the confirmation round-trip (though confirmation_token is documented in the schema) and any guidance relative to create_reminder; with no output schema, return behavior is reasonably left implicit.

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 meaning above the schema: the key semantics ("One request_key can be applied only once; a changed intent with the same key fails") go beyond the schema's neutral "Stable unique request identity." It also ties the operation to the exact lead, body, and due date, grounding three of the six parameters in intent.

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 a concrete verb and resource ("Create a scoped note or reminder") and adds the scoping constraint, so an agent knows this writes a note attached to a lead. However, it never distinguishes itself from the sibling create_reminder, and by claiming to create both notes and reminders it actively blurs the boundary with that sibling.

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 a clear invocation precondition: the call must follow "an explicit confirmation of the exact lead, body, and due date," which tells the agent when it is safe to proceed. It stops short of naming alternatives (create_reminder, list_reminders) or exclusions, so routing between the note/reminder siblings is left to inference.

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