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

Annotations only state readOnlyHint=false, destructiveHint=false and openWorldHint=false. The description goes beyond that by disclosing that no message is sent, that the token is single-use, that it expires in ten minutes, and that the preview reflects the current state. It does not say what happens when expectedVersion is stale, or confirm that no persistent state changes besides the token.

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 short sentences contain zero filler. The non-sending guarantee is front-loaded as the final clause of the first sentence and then reinforced, so the agent's main risk, sending an email by mistake, is immediately resolved.

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?

A return-value explanation is not needed because an output schema exists, and the safety profile is adequately covered. It does not explain the three required parameters or the token's required lifecycle, including what to do when expectedVersion conflicts.

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?

All three required parameters (quoteId, expectedVersion, idempotencyKey) have 0% schema description coverage, so the description alone must explain them. It instead only implies the ideas of a version check and a single-use key, without mapping them to the fields or giving formats.

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 and resource: it 'previews the exact current quote recipient and payload' and stores a confirmation token. 'This does not send' clearly separates it from the send_quote sibling, so an agent can tell the two apart. It loses one point only because it never names the tool that consumes the token.

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?

The ten-minute one-use token implies this is the step that runs before an actual send, but the description does not explicitly say 'call this before send_quote' or name any alternative. It also does not say when to skip it, such as a deliberate preview-only check. The usage guidance must be inferred from the description.

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