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

Annotations cover non-read-only, open-world and idempotent, but the description goes well beyond them: it explains that the same idempotency_key never creates a second request, enumerates the three result states and what each means for what was actually sent, and specifies the post-call obligations (tell the person it is not a booking, where the answer goes, when to schedule request_status). That is exactly the context an agent needs before mutating anything.

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?

Front-loaded with the highest-stakes warning (acts for the user), then scope, then payload, then result states, then follow-up duties. Nearly every sentence carries operational value, though the browser-instruction tail repeats ground already covered by the server instructions and the emoji-flagged opening is a little shouty.

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 nine-parameter mutating tool with a nested customer object and no output schema, the description covers precondition, scope, idempotency, all three return states, the whatsapp_url handoff, and the required follow-up narration. An agent could invoke it correctly and handle every outcome without further information.

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 coverage is 67% and the description supplies meaning for the important gaps: it enumerates the payload fields in plain language, explains idempotency_key semantics and the retry contract, and clarifies that next_steps.check_again_after is a pause rather than a promised reply time. It does not add anything about date/time locality or the quantity bounds beyond what the schema already states.

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 ('Sends what, when, how many, which branch and the person's name and contact') and immediately scopes it to businesses that take requests through Versum via a verified owner. The title and opening line make clear it is a request, not a booking, which separates it from siblings like book_slot and place_order.

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 an explicit precondition ('call it only after the user has explicitly agreed to this exact action') and states it is never to be used on the agent's own judgement. It also names the fallback outcomes (link_given, no_channel) that redirect the agent elsewhere, and closes with the separation rule that requesting must stay distinct from reading, quoting and ordering.

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