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

Goes well beyond the annotations by disclosing the external side effect (the business receives the message plus the person's name, email and phone, i.e. PII is transmitted) and the callback phone requirement. It does not say whether repeated calls produce duplicate messages or what a successful response looks like, which leaves some gaps for a destructive, non-idempotent write.

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 sentences, no waste, front-loaded with the action and its recipient, followed by effects and then the confirmation gate. Each sentence carries distinct information.

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?

Covers the risky parts of an open-world, destructive, non-idempotent write: recipient eligibility, data disclosure, and the required human confirmation. The main remaining gap is return behavior (no output schema, and the description doesn't say what confirmation the caller gets).

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?

With 0% schema description coverage, the description carries the burden well: it defines what 'kind' selects and where to look for valid values, notes phone is required for callbacks, and explains the gate that 'confirmed' represents. It leaves formats for business_id, email and message unaddressed, so not fully complete.

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 (send) plus the concrete resource types (question, quote request, callback request) aimed at a business. It also distinguishes itself from get_business by pointing there for the allowed kinds, so an agent can tell the two apart immediately.

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?

Explicit preconditions: the business must have can_contact, kinds are discoverable via get_business, phone is required for callbacks, and the agent must confirm the message and details with the person before calling with confirmed=true. This is a full when/how-to-use recipe with no inference required.

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