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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive), yet the description adds real context: nothing is stored or sent, an approval_code plus consent and notice text is returned, and the person must be shown everything before approval. Minor gap: it does not say whether preview output can go stale relative to the lawyer's live availability, or how after_yes.arguments is shaped.

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 description is front-loaded with the trigger and the outcome, then the approval protocol, then the service disclaimer, so ordering is sound. It is dense and somewhat run-on in a single paragraph, and the closing listing-service/no-paid-placement sentence, while relevant to disclosure, sits outside the tool's mechanics.

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 what the agent must do (gather, draft, surface, await explicit consent, re-run on edits) and what comes back at a high level without duplicating the output schema. Nothing needed to invoke it correctly appears to be missing.

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 73%, and the description compensates for much of the remainder by naming the facts to collect (issue type, location, help wanted, timing, optional budget, contact method), which maps onto practice_area, state/matter_location, assistance, timing, budget and preferred_contact_method. It does not explain attorney_id vs entry_id, nor the required nature of preferred_contact_method and the nested contact object.

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 opens with a specific verb and resource ('Builds a short, editable first message') scoped precisely to ONE lawyer, and the title reinforces that nothing is sent. It is unambiguously distinguishable from the sibling send_client_message, which it names as the follow-on action.

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 states the triggering user intent ('wants to contact ONE lawyer' / 'write my message'), the exact handoff condition ('only after an explicit yes call send_client_message with after_yes.arguments'), and the re-entry rule ('Any change by the person means calling this again and asking again'). No alternatives are left to inference.

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