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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description is not obligated to establish that it mutates state. It nonetheless adds genuinely non-obvious behavior: the call never deletes directly, it returns status='confirmation_required' with an action_id and plan_token, and the write only occurs after confirm_action. It doesn't say whether the deletion is reversible or what happens to linked records.

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 scope constraint and the confirmation behavior are front-loaded and each sentence adds information. There is slight redundancy between 'Proposed for confirmation before it runs' and the CONFIRMATION sentence that follows it.

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 one-parameter destructive tool with no output schema, the definition supplies the essential contract: tenant scoping, the confirmation gate, and the response fields to expect. It leaves unresolved what a successful post-confirmation response looks like and whether a missing/non-tenant lead errors or silently succeeds.

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?

The single lead_id parameter has 0% schema description coverage, so the description carries the burden. It does clarify that the id is scoped to the caller's tenant and that a foreign id silently deletes nothing, which is useful semantics, but it gives no format or example for the integer|string union.

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 (Delete) and resource (CRM lead) qualified by scope ('by id from the caller's active workspace'), which cleanly separates it from siblings like update_lead, get_lead, and the unrelated delete_* tools. An agent can identify the operation without opening the schema.

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 explains the tenant boundary ('only a lead in the caller's tenant is reachable; a wrong-tenant id deletes nothing') and names the follow-up path via confirm_action, giving clear operational context. It stops short of explicit when-not-to-use guidance (e.g., prefer update_lead to modify rather than remove).

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