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

Annotations already cover the safety profile (mutating, idempotent, non-destructive, closed-world), so the description's added value is the precondition/refusal set, which is genuinely non-obvious and prevents wasted calls. It also restates the idempotency retry contract, though that duplicates the schema field description, and it says nothing about downstream effects such as follow-up steps being queued.

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?

Four compact sentences, front-loaded with the action and its UI analogue before the refusal rules. A couple of clauses are run-on ('as the thread header's Track this as a new lead does, for a customer asking about new work'), but no sentence is filler.

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 mutating tool with no output schema, the definition covers preconditions well but omits what a successful call yields (lead identifier, ownership, whether follow-up steps start immediately) and leaves two of four parameters unexplained. Adequate to invoke safely, incomplete for predicting 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?

With only 25% schema description coverage, the description must carry most parameter meaning; it explains 'request' as 'what they asked for, in a line' and reinforces idempotency_key reuse. However, 'conversation_id' is never explained (presumably the thread id) and 'channel' is left entirely undescribed — whether it defaults from the conversation or must match it is unstated.

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 ('Opens a lead for this thread's contact') and anchors it to the product's own UI affordance ('the thread header's Track this as a new lead'), which removes ambiguity against sibling lead tools like declare_lead_sources, set_lead_outcome and move_lead_journey.

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?

The trigger condition is explicit ('for a customer asking about new work'), and the exclusion list is concrete: refused when lead follow-up is off, no contact on the thread, or contact is staff/applicant/spam. It stops short of naming a sibling alternative for the cases where this is refused, but the when-to-use guidance is clear without it.

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