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

Annotations only declare write/open-world/non-destructive; the description adds the materially important framing that this opens a conversation rather than committing to a booking, order, payment or hold, and that no email, phone or account is required. It also discloses a privacy constraint on reply_token and the follow-up path (inquiry_status, follow_up_business). Nothing here contradicts the annotations.

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 action and its target, then layered as short imperative rules with no filler. Every sentence carries an operational constraint (when to send, what it is not, token privacy, no duplicates, sibling routing), so nothing is 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?

With no output schema, the description does the right work by implying a reply_token is returned and pointing to inquiry_status for reading replies. The remaining gap is that request_type is never explained and the business identifier's expected form is only hinted at via "from business_info".

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%, so the description carries the burden, and it does loosely map three parameters: business ("the exact business from business_info"), customer_name ("the customer's name"), and message ("their message"). However, the request_type enum with its six values and "question" default is never mentioned, and no format or constraint detail (e.g. the 500-char message cap) is added, leaving a real gap at 0% coverage.

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?

States a specific verb and resource ("Send a request to the exact business from business_info") and immediately bounds what the action is not ("not a confirmed booking, order, payment or inventory hold"). It explicitly distinguishes itself from the two nearest siblings, ask_business (business-owner contact) and follow_up_business (continuation), so an agent can route without opening another 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?

Gives a positive trigger ("send only when the customer asks you to"), a negative trigger ("Do not send a second initial request when you already have a conversation"), and a named alternative for a different intent ("To contact another business as a business owner, use ask_business instead"). It also directs the agent to ask only for missing details, which is a concrete pre-send rule.

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