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

With no annotations, the description carries the full burden and does well: it discloses that nothing is held, no details are captured, and precisely what is returned (a WhatsApp deeplink with pre-filled text and the contact page address). Missing only edge behavior such as whether the message text or contact address varies by context.

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 key caveat ('not open yet') is front-loaded before any behavior is described, which is the right ordering. Four short clauses with little waste, though the phrasing about an assistant booking a call is slightly indirect compared to just stating what the tool returns.

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 zero-parameter, no-output-schema, no-annotation tool, the description covers the essentials: what is returned, that nothing is persisted, and how to present the result to the user. The only real gap is the unreconciled discrepancy with the name and the absence of explicit sibling routing.

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?

The tool takes zero parameters, so the baseline is 4. The description reinforces this by stating it 'takes no details,' which confirms to the agent that no arguments need to be gathered before calling — a genuinely useful signal here.

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 is concrete about the effect: it returns a WhatsApp link with a pre-written neutral message plus the contact page address, and explicitly states it 'holds nothing and takes no details.' However, the tool name 'confirm_booking' implies a booking confirmation that the description says cannot happen, and the mismatch is never reconciled. It also never names the sibling it substitutes for (book_call), leaving the agent to infer the relationship.

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?

'Show your user the link if they want to talk to the agent' gives a clear condition for using the output, and 'booking a call ... is not open yet' implies this is the fallback path. But it never states when to call this versus book_call, check_booking, or cancel_booking, so routing against 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.