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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower, and the description still adds valuable context the annotations cannot: a required preview-then-approve gate and the requestId-based confirmation/recovery protocol. The trailing 'Claim live only when status is active' is underspecified (presumably a pointer to soclo_ads_operation_status) and slightly muddies an otherwise informative line.

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?

It is short and the approval protocol is front-loaded after a one-line name restatement, but the telegraphic fragments ('Spending/deletion: ...', 'Claim live only when status is active') cost clarity for their brevity. The closing 'Fields: soclo://tools/...' URI adds only a pointer, not usable information.

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 destructive, open-world mutation with six parameters, a nested object, no output schema and 50% schema coverage, the description covers the safety workflow but leaves the targeting semantics (formId/leadId, accountId vs adAccountId) and post-delete state entirely unaddressed. An agent could satisfy the confirm protocol yet still pick the wrong identifiers.

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 50% schema description coverage and a nested 'parameters' object, the description should compensate more than it does; it only reinforces confirm and requestId, which the schema already documents. Nothing explains why both accountId and adAccountId exist, when formId (required) versus leadId (optional) selects the target, or what platform should contain.

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 ('Delete a test lead'), which cleanly separates it from soclo_ads_create_test_lead and the broader lead-listing/archiving tools. It never names a sibling alternative or clarifies the distinction between deleting a test lead versus soclo_leads_archive or soclo_ads_archive_lead_form, so differentiation is only implied by the noun phrase.

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 encodes a real workflow ('preview, then owner-approved confirm:true with the same requestId'), which tells the agent the ordering constraint and that an owner approval step is required. It does not say when to prefer this tool over archiving or removing a lead through another path, and 'Claim live only when status is active' is too cryptic to function as actionable guidance.

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