Check a lead

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

With no annotations, the description carries the full burden and does well: it discloses the return shape (verdict, 0-100 score, weighted reasons, policy pass/fail), the cost model (1 credit fast, 5 deep, unknowns free), and the semantic difference between tiers ('deep ... looks for extra evidence about the person'). It omits auth requirements and rate limits, so not a full 5.

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?

Three tight sentences, front-loaded with purpose before output details, then tier pricing. No filler and every clause carries information the agent needs to choose a tier and interpret results.

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?

There is no output schema, so the description correctly compensates by describing the return payload, and it covers costs and tier semantics. The nested context object ('Everything you know about the lead') is not explained as to whether or how it improves accuracy, which is the main remaining gap for a tool with two nested object parameters.

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 100%, so the baseline is 3, but the description earns extra credit by adding meaning the schema lacks: that 'fast' is the default and costs 1 credit while 'deep' costs 5, and that deep searches for additional person-level evidence. The policy object's override behavior is only stated in the schema, not the description.

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: 'Review one email address for deliverability.' The word 'one' frames it as a single-address check, distinguishing it from batch-oriented siblings like check_batch and batch_status. It also enumerates the verdict vocabulary, so the agent knows exactly what kind of result to expect.

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 description explains the fast-vs-deep tier tradeoff and their credit costs, which is real usage guidance for parameter selection. However, it never states when to reach for this tool versus check_batch/batch_status or other lead tools, and gives no exclusions or prerequisites. Usage is implied rather than directed.

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