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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces them with 'Stores and sends nothing' while adding behavior the annotations cannot express: it returns recipient, message, contact fields, notice, consent text, and an approval_code, requires showing everything to the person, and only proceeds on an explicit yes. This is exactly the extra context a multi-step consent flow needs.

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 deprecation/redirect is first, followed by trigger, build behavior, returns, and the send-after-consent rule in a logical order. It is dense but nearly every clause carries operational meaning; the closing listing-service disclaimer is relevant but slightly off-topic for this specific tool.

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 an 11-parameter tool with a nested contact object and an output schema, the description covers the workflow, the preview-only guarantee, what to show the user, and the handoff to sending. Minor gaps remain around identifying the lawyer (attorney_id vs entry_id) and how the edited message parameter is used on re-calls.

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 73%, and the description maps user-facing concepts onto fields well: type of legal issue, location, help wanted, timing, optional budget, contact method. It does not explain attorney_id vs entry_id or the message-edit parameter beyond implication, so a little meaning is still left to the 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 action (build a short, editable first message to one lawyer) and explicitly disambiguates from siblings: it names preview_client_message as the current tool and send_client_message as the follow-up. The deprecation notice is front-loaded, so an agent immediately knows what this tool is and why it exists.

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 a concrete trigger ("Use when the person wants to contact ONE lawyer they picked"), names the replacement tool, and names the exact next step after explicit consent (send_client_message with after_yes.arguments). It also states the re-call rule on any user change, so the agent knows both when to use and when to loop back.

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