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

Annotations only give the safety profile (not read-only, not destructive, closed-world); the description goes well beyond that by disclosing the approval workflow: paymentUrl, transferPhone and a higher spending limit on an active plan stall as pending_approvals until the owner approves in the dashboard, while other fields apply immediately. It also bounds the tool by stating complete:true never activates voice, ports a number, collects a card or enforces billing. The only gap is a precise statement of what the call returns when an approval is queued, though waiting_for_owner and approval_id are named.

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 prerequisite and the read-first instruction are front-loaded, and every clause carries information about scope, approvals or boundaries. It is dense with parentheticals and long compound sentences, which makes it harder to scan than it needs to be, but little is genuinely redundant.

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 mutation tool with no output schema and an undocumented nested schema, the description supplies the prerequisites, the approval branching, the meaning of complete, and explicit non-goals. An agent can call it correctly and interpret an approval-queued outcome 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 0% across a nested settings object with roughly nineteen properties, so the description carries real weight: it explains the approval consequence of transferPhone and paymentUrl and the exact meaning of complete:true, which the schema states nowhere. It still leaves most nested settings properties (voice, handoff, coverage, quietHours, bookingMode, etc.) undocumented beyond their names, so it does not fully compensate for the coverage gap.

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 names a specific verb and resource (update front desk/preferences) and enumerates the concrete settings in scope: payment links, optional suggestions, spending preferences and call handling. It explicitly routes knowledge editing elsewhere (update_receptionist), so the agent can separate this tool from its closest sibling without opening either schema.

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?

It states the precondition (owners only, needs sign-in), mandates a read-before-write step (read front_desk first), restricts scope to preferences the owner explicitly requested, and names the alternative tool for knowledge changes. That is explicit when-to-use, when-not and alternative routing.

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