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

Discloses asynchronous behavior, credit consumption, API key requirement, and effect of useAI. Annotations indicate openWorldHint=true and idempotentHint=false, but the description adds richer context about side effects and credits. No contradiction.

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 moderately concise, with a clear first sentence stating the core function, followed by important usage and caution information. The structure is effective, though the last sentence on useAI could be integrated more tightly.

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?

Given the tool's complexity (asynchronous, credit-based, with filters), the description covers key aspects: async workflow, credit warning, and API key requirement. It lacks explicit mention of output schema, but the return is just jobId which is implied. Overall, reasonably complete.

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 has 100% coverage for all parameters, so baseline is 3. The description adds meaning for useAI (spends credits) and the query parameter (describing ideal lead) beyond schema. It doesn't add detail for filters, but schema already covers them.

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 clearly states the tool starts an AI lead-search job and returns a jobId immediately. It distinguishes from siblings by noting 'Use it to find NEW leads; use list_leads for ones already saved.' The verb and resource are specific.

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?

Explicitly explains when to use this tool (to find new leads) versus list_leads, and provides a workflow: poll get_search_job_status and then list_leads. Also warns against using it to check progress and explains credit consumption.

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