send_trusted_message

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

The description usefully discloses the most important behavioral fact — no real SMS is sent — and that only one consumption is possible. However, it sits in tension with destructiveHint=true / readOnlyHint=false: it never explains that the handoff token is consumed/invalidated, so an agent is left to reconcile "simulate" with a destructive annotation on its own.

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 short sentences with no filler, and the safety guarantee lands early. But two of the three sentences are fragments that state constraints rather than the operation, so the paragraph reads as warning copy rather than a front-loaded description.

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 single-parameter, no-output-schema tool this covers the decisive safety facts (simulation only, single use, consent must be a real credential) that an agent could otherwise get dangerously wrong. The remaining gap is the handoff_id lifecycle, which is a meaningful but secondary omission.

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?

One parameter (handoff_id) with 0% schema description coverage and the description never mentions it or says what a valid handoff is. The phrase "independently approved preview" only loosely implies the ID is an approval artifact; an agent gets no guidance on where to obtain it or that it is single-use.

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?

"Simulate an independently approved preview once" gestures at the action but never says what is being previewed (an SMS to a trusted contact) or that the handoff is consumed. Combined with the name and "Never sends a real SMS" an agent can infer the domain, but the sentence itself is vague and would be opaque standing alone.

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 implicitly requires a prior independent approval and notes the action happens "once", which hints at sequencing after prepare_handoff, but no sibling is named and there is no explicit when-to-use / when-not-to-use. The line about a chat "yes" not being a consent credential is a constraint, not usage routing.

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