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

Annotations only declare that this is a non-read-only, open-world, non-idempotent, non-destructive call; the description goes well beyond that by disclosing exactly who receives the data (Contrast Therapy Finder, which forwards to a manufacturer), what the third party does with it (gets a real quote including delivery and installation requirements), and a privacy commitment that nobody else contacts the person unless they ask. Combined with the explicit consent/confirmation flags, the agent knows the data-sharing consequence and the irreversibility-adjacent risk of submitting on someone's behalf.

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 opening sentence is front-loaded with the action, recipient, and scope, and the REQUIRED BEFORE CALLING block is a clean, scannable checklist ending in the exact call flags. It is dense but every clause is operational — the only mild redundancy is restating the manufacturer-sharing step in both the narrative and the consent instruction.

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 14-parameter, open-world submission tool with no output schema, the description covers who gets the data, what obligations exist, and what gating flags to set — the information an agent most needs to avoid a bad submit. It leaves one meaningful gap: what the person should expect afterward (how and when the quote arrives, and what the tool returns on success), which matters because there is no output schema to explain the result.

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 71%, with the address, phone, zip, notes, consent, user_confirmed, business, and agent_name fields already well documented inline. The description reinforces that all required values must come from the person rather than being fabricated and ties consent/user_confirmed to the confirmation workflow, but it adds no field-level meaning about the four undescribed enums (interest, use, budget, timeline) beyond what their values imply. Baseline 3 for a mostly-covered schema.

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 states a specific verb and resource — sending a free, no-obligation quote request for a sauna and/or cold plunge, for home or commercial use — to a named recipient (Contrast Therapy Finder). That is far more precise than the title alone, but it never names or contrasts with the sibling tools (get_equipment_pricing, find_studios), so an agent must infer that pricing lookup is the alternative path rather than being told.

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?

It gives an explicit pre-call protocol: collect every required detail from the person, never guess or reuse details given for another purpose, show an exact summary of what will be sent, explain that the details go to a manufacturer, and obtain an explicit yes before calling with user_confirmed=true and consent=true. What is missing is guidance on when this tool is the right choice versus the pricing tool — e.g., whether a researching user who only wants ballpark numbers should be routed to get_equipment_pricing first.

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