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

Annotations cover only the generic safety profile (readOnlyHint=false, destructiveHint=false); the description adds the crucial behavioral facts: nothing is actually sent, the draft must be shown to the person, amounts are validated and refused if they don't match the invoice, and unagreed fees/collections language is forbidden. These are exactly the non-obvious traits an agent could otherwise get wrong.

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?

Purpose and the 'never sends it' caveat are front-loaded, and the content rules and follow-up are ordered logically. It is dense and long for a single tool, but nearly every clause carries operational information rather than restating structured fields.

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?

No output schema exists, yet the description covers prerequisites, content rules, prohibited content, the human-in-the-loop step, the follow-up recording call, and the effect. An agent has everything needed to invoke it correctly without further context.

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 description coverage is 100%, so baseline is 3, but the description adds content requirements beyond the schema: the body must carry the invoice number, amount open, due date, and pdf_url, and must be written in the person's voice. It does not elaborate on soon_because beyond the schema, keeping it at 4.

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 specific verb and resource — write a payment reminder for an overdue invoice — and immediately scopes it as a draft that Saybooks never sends. This cleanly separates it from solo_reminders (listing) and solo_reminder_outcome (recording that it went).

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 the precise qualifying condition (invoice past its due date with money still open, with solo_outstanding fields to check), names the prerequisite and follow-up tools (solo_get_document, solo_reminder_outcome), and explains the escalation logic across first/second/final reminders. Alternatives and when-to-use are explicit.

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